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

    Neuronpedia

    INDEX
    Explanations

    survival

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    المكان
    -0.59
    StructEnd
    -0.56
    Хьажоргаш
    -0.54
    ğlık
    -0.54
    rungsseite
    -0.54
    QX
    -0.53
    ########.
    -0.53
     Diſ
    -0.53
    teinte
    -0.52
     дописавши
    -0.52
    POSITIVE LOGITS
    MeasureSpec
    0.52
    tonsoft
    0.49
    MockMvc
    0.47
     <<<<<<<<<<<<<<
    0.47
    ski
    0.44
     estimés
    0.44
    Aiheesta
    0.43
     lympho
    0.43
     ModelExpression
    0.43
     liberalism
    0.42
    Act Density 0.009%

    No Known Activations