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

    Neuronpedia

    INDEX
    Explanations

    code related to displaying something

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .slider
    -0.07
    pipes
    -0.06
     tended
    -0.06
     Credentials
    -0.06
     Allowed
    -0.06
     divorced
    -0.06
    .drawable
    -0.06
    /s
    -0.06
     toolbox
    -0.06
    OBJECT
    -0.06
    POSITIVE LOGITS
     بان
    0.07
     colabor
    0.06
     Oliveira
    0.06
    _instruction
    0.06
    /free
    0.06
    меть
    0.06
    iples
    0.06
     플
    0.06
    .vm
    0.06
    prit
    0.06
    Act Density 0.040%

    No Known Activations