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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     distrust
    -0.07
    _expected
    -0.07
     grandi
    -0.07
    .currency
    -0.06
     propaganda
    -0.06
     değişiklik
    -0.06
     건
    -0.06
     olmak
    -0.06
    .Prop
    -0.06
    .Port
    -0.06
    POSITIVE LOGITS
     gymn
    0.07
     rationale
    0.06
     finale
    0.06
    Mutation
    0.06
     exclusively
    0.06
     instructor
    0.06
    fusc
    0.06
    زة
    0.06
     selective
    0.06
    Clr
    0.06
    Act Density 0.026%

    No Known Activations