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

    Neuronpedia

    INDEX
    Explanations

    Code/Technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alie
    -0.07
     obedient
    -0.06
    кість
    -0.06
    完成
    -0.06
    _SITE
    -0.06
     contain
    -0.06
    셨
    -0.06
    انات
    -0.06
    �
    -0.06
    одатель
    -0.06
    POSITIVE LOGITS
    IW
    0.07
    kJ
    0.07
    _rating
    0.07
    五
    0.07
    _fu
    0.06
     testified
    0.06
    Im
    0.06
    Vm
    0.06
     �
    0.06
    _FM
    0.06
    Act Density 0.000%

    No Known Activations