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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    #+#
    -0.81
    rungsseite
    -0.63
    ագրություններ
    -0.59
    .*")]
    -0.59
    +#+#
    -0.58
    makeConstraints
    -0.57
    tvguidetime
    -0.54
     testemun
    -0.53
    Tracce
    -0.51
    writeFieldEnd
    -0.51
    POSITIVE LOGITS
    行政区划
    0.52
    bootstrapcdn
    0.49
    ViewImports
    0.48
     Knud
    0.48
    ScopeManager
    0.48
    pos
    0.44
    SuppressMessage
    0.44
    Elon
    0.42
    issons
    0.42
     diametro
    0.42
    Act Density 0.000%

    No Known Activations