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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .measure
    -0.07
    Baseline
    -0.07
    戦
    -0.06
    %x
    -0.06
    Validate
    -0.06
    Bed
    -0.06
    =index
    -0.06
     Alger
    -0.06
    _arg
    -0.06
     умов
    -0.06
    POSITIVE LOGITS
    JP
    0.07
     harassing
    0.06
    汇
    0.06
    【
    0.06
    :[],↵
    0.06
    icontains
    0.06
     και
    0.06
    أم
    0.06
    ”。↵↵
    0.06
    Hashtable
    0.06
    Act Density 0.015%

    No Known Activations