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

    Neuronpedia

    INDEX
    Explanations

    model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Popup
    -0.07
    inspection
    -0.07
     haf
    -0.07
    mana
    -0.06
    terminal
    -0.06
    ιώ
    -0.06
     waterproof
    -0.06
    ैम
    -0.06
     humiliation
    -0.06
    PWM
    -0.06
    POSITIVE LOGITS
    :::::::
    0.07
    طم
    0.06
     عفش
    0.06
    TabControl
    0.06
     предназнач
    0.06
    概
    0.06
     Mens
    0.06
    ático
    0.06
     {[%
    0.06
    이고
    0.06
    Act Density 0.032%

    No Known Activations