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

    Neuronpedia

    INDEX
    Explanations

    days and origins

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     native
    -0.91
     nativo
    -0.74
     Native
    -0.72
    native
    -0.66
    ViewFeatures
    -0.66
    JNIEnv
    -0.61
    Native
    -0.60
    Monday
    -0.57
     nativa
    -0.57
    monday
    -0.55
    POSITIVE LOGITS
    berg
    0.60
    akin
    0.55
    to
    0.53
    himovic
    0.53
    uteness
    0.52
    men
    0.52
     Parenthood
    0.52
    base
    0.51
     πρό
    0.51
     Edition
    0.51
    Act Density 0.225%

    No Known Activations