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

    Neuronpedia

    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ayrıca
    -0.07
     Elasticsearch
    -0.06
     eccentric
    -0.06
     Castillo
    -0.06
    indrome
    -0.06
     safer
    -0.06
    jp
    -0.06
    /tutorial
    -0.06
     Benedict
    -0.06
     evet
    -0.06
    POSITIVE LOGITS
    RIES
    0.07
     Spray
    0.07
     sprayed
    0.06
     privately
    0.06
     args
    0.06
     commentaire
    0.06
     linear
    0.06
     purge
    0.06
    (varargin
    0.06
                                    
    0.06
    Act Density 0.010%

    No Known Activations