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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    服
    -0.07
     HM
    -0.07
     Charity
    -0.07
     JP
    -0.06
    utra
    -0.06
     Miguel
    -0.06
    isté
    -0.06
    evil
    -0.06
    (COM
    -0.06
     proceeded
    -0.06
    POSITIVE LOGITS
    Procedure
    0.07
    Modification
    0.07
    .notes
    0.07
    WithTitle
    0.07
    .assertRaises
    0.06
    laşma
    0.06
    _ALIGNMENT
    0.06
     parentId
    0.06
    _candidates
    0.06
    Sizer
    0.06
    Act Density 0.004%

    No Known Activations