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
     climax
    -0.07
     Hir
    -0.06
     Ler
    -0.06
     Bloss
    -0.06
     Material
    -0.06
    /Branch
    -0.06
     Nullable
    -0.06
     Herz
    -0.06
     Apollo
    -0.06
    Mana
    -0.06
    POSITIVE LOGITS
    @mail
    0.07
    unsigned
    0.07
    TextInput
    0.06
    _aligned
    0.06
    侧
    0.06
    reb
    0.06
    -producing
    0.06
    であり
    0.06
     italiano
    0.06
     ticari
    0.06
    Act Density 0.081%

    No Known Activations