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

    Neuronpedia

    INDEX
    Explanations

    sg

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Å
    -0.06
     Cristina
    -0.06
    /*
↵
    -0.06
     pond
    -0.06
     titanium
    -0.06
    /*****************************************************************************↵
    -0.06
     radiator
    -0.06
     allerg
    -0.06
     detergent
    -0.06
    ==========↵
    -0.06
    POSITIVE LOGITS
    OptionPane
    0.07
     NGO
    0.06
    .SendMessage
    0.06
    rate
    0.06
    مول
    0.06
     registering
    0.06
    غط
    0.06
    ANC
    0.06
    Sexy
    0.06
     parch
    0.06
    Act Density 0.005%

    No Known Activations