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

    Neuronpedia

    INDEX
    Explanations

    import

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.84
     Roskov
    -0.83
    LookAnd
    -0.82
     scolaires
    -0.74
    Jereo
    -0.74
    IsContent
    -0.72
    IndentedString
    -0.71
     femininas
    -0.69
     beginnetje
    -0.69
    complexContent
    -0.68
    POSITIVE LOGITS
     observe
    0.58
     experience
    0.55
     realize
    0.50
     realise
    0.47
     note
    0.46
     record
    0.45
     measure
    0.44
     find
    0.40
    AsUp
    0.39
     identify
    0.39
    Act Density 0.000%

    No Known Activations