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

    Neuronpedia

    INDEX
    Explanations

    words pointing out or emphasizing something.

    oai_token-act-pair · gemini-2.0-flash

    thing, even (conversational)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.81
    __;
    -0.68
     "..\..\
    -0.66
     Offisielt
    -0.66
     theirs
    -0.64
    enumii
    -0.63
     anyway
    -0.63
    ValueStyle
    -0.62
    Hochspringen
    -0.62
     part
    -0.60
    POSITIVE LOGITS
    AxisAlignment
    0.65
     doInBackground
    0.63
    '
    0.63
     excitations
    0.55
    viewDidLoad
    0.53
    setVerticalGroup
    0.52
     cilia
    0.51
     lädt
    0.51
    CGRectMake
    0.49
     popolare
    0.49
    Act Density 2.058%

    No Known Activations