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

    Neuronpedia

    INDEX
    Explanations

    an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Defaults
    -0.07
    Hey
    -0.07
    ató
    -0.07
    194
    -0.07
    mdi
    -0.06
    .people
    -0.06
    ırı
    -0.06
    .labelControl
    -0.06
    editar
    -0.06
     tavsiye
    -0.06
    POSITIVE LOGITS
     techniques
    0.07
    asts
    0.07
     Invocation
    0.06
     punct
    0.06
    _DISPLAY
    0.06
     demir
    0.06
    lay
    0.06
    _DEST
    0.06
     unmatched
    0.06
     insider
    0.06
    Act Density 0.008%

    No Known Activations