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

    Neuronpedia

    INDEX
    Explanations

    dash

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bulb
    -0.08
    떻
    -0.07
    Spell
    -0.07
     Paypal
    -0.07
    Personal
    -0.07
    zn
    -0.07
     Payne
    -0.07
    _ph
    -0.07
    퓨
    -0.07
     kneeling
    -0.07
    POSITIVE LOGITS
    回答
    0.07
    )data
    0.07
    _ARGUMENT
    0.07
    .gl
    0.07
    大理
    0.07
     cared
    0.07
    跎
    0.07
    //@
    0.07
     Regel
    0.06
     LGBTQ
    0.06
    Act Density 0.006%

    No Known Activations