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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    989
    -0.07
     지역
    -0.07
     nécessaire
    -0.06
    ичество
    -0.06
     kommer
    -0.06
     forts
    -0.06
     noen
    -0.06
     худож
    -0.06
    cession
    -0.06
    _true
    -0.06
    POSITIVE LOGITS
     counterparts
    0.07
    Carrier
    0.06
    매
    0.06
    be
    0.06
    heel
    0.06
    ải
    0.06
    angled
    0.06
     �
    0.06
    +
    0.06
    ++;
    0.06
    Act Density 0.002%

    No Known Activations