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

    Neuronpedia

    INDEX
    Explanations

    Code and file paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    了好几
    -0.07
     조금
    -0.07
     Probability
    -0.07
     Gio
    -0.07
    Character
    -0.07
    が高い
    -0.07
     garnered
    -0.07
     drastic
    -0.07
    _geo
    -0.07
    prd
    -0.06
    POSITIVE LOGITS
    议员
    0.07
    +x
    0.07
     conven
    0.07
    .onChange
    0.07
    !=(
    0.07
    下行
    0.07
    Clear
    0.06
     Comm
    0.06
    घ
    0.06
    MISSION
    0.06
    Act Density 0.000%

    No Known Activations