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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bulgaria
    -0.08
     outlets
    -0.07
    18
    -0.07
    มอ
    -0.07
     allergy
    -0.07
     trunk
    -0.07
    得
    -0.07
    itas
    -0.06
     тогда
    -0.06
     wounded
    -0.06
    POSITIVE LOGITS
    .SDK
    0.07
    .fx
    0.07
    осп
    0.06
     mgr
    0.06
    .tsv
    0.06
    ltre
    0.06
     створ
    0.06
    ميل
    0.06
    _FF
    0.06
    ismu
    0.06
    Act Density 0.014%

    No Known Activations