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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thrilling
    -0.07
    (exc
    -0.07
    _velocity
    -0.07
    _loading
    -0.06
    ату
    -0.06
    .Escape
    -0.06
    .address
    -0.06
     Henderson
    -0.06
     surrounded
    -0.06
     Muk
    -0.06
    POSITIVE LOGITS
    елем
    0.07
    cm
    0.06
    ..\
    0.06
     retorno
    0.06
    音
    0.06
    Ｅ
    0.06
     requirements
    0.06
     False
    0.06
    RSS
    0.06
    dao
    0.06
    Act Density 0.159%

    No Known Activations