Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Compromise/generosity

    np_max-act · gemini-2.0-flash

    This neuron detects first‐person boasts or self-promotional statements (e.g. “I give you everything…,” “I even put money in the bank,” “I’m a good woman,” “I got beauty, style, class,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     듣
    -0.06
     فکر
    -0.06
     Gun
    -0.06
    block
    -0.06
     نمود
    -0.06
     clipboard
    -0.06
     받아
    -0.05
    IBAction
    -0.05
    .Child
    -0.05
    Think
    -0.05
    POSITIVE LOGITS
    .SaveChanges
    0.07
    existence
    0.07
    Configurer
    0.06
    (Project
    0.06
    ","");↵
    0.06
    _mE
    0.06
    };
↵
    0.06
    SVG
    0.06
     清
    0.06
    istr
    0.06
    Act Density 0.034%

    No Known Activations