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

    Neuronpedia

    INDEX
    Explanations

    programming and articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    432
    -0.07
     海
    -0.07
     �
    -0.07
     힘
    -0.07
    ã
    -0.07
    .sec
    -0.07
     approval
    -0.07
    719
    -0.06
    lices
    -0.06
    ermo
    -0.06
    POSITIVE LOGITS
     incapable
    0.07
    ’Brien
    0.07
     Attack
    0.06
     Bolton
    0.06
    'Brien
    0.06
    _mov
    0.06
    WebResponse
    0.06
     Holt
    0.06
    attack
    0.06
     Babies
    0.06
    Act Density 0.000%

    No Known Activations