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

    Neuronpedia

    INDEX
    Explanations

    wear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     juice
    -0.07
     railway
    -0.07
     êtes
    -0.07
    ülük
    -0.07
     RIGHTS
    -0.06
     Were
    -0.06
     Dialogue
    -0.06
     Directive
    -0.06
    Policy
    -0.06
    orris
    -0.06
    POSITIVE LOGITS
     sign
    0.07
    .col
    0.07
     Bian
    0.07
     significa
    0.07
    _BASE
    0.06
    leased
    0.06
     unveiling
    0.06
    .entry
    0.06
    comments
    0.06
     милли
    0.06
    Act Density 0.006%

    No Known Activations