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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    once
    -0.08
    -medium
    -0.07
     toys
    -0.07
    gabe
    -0.06
    orption
    -0.06
     Cone
    -0.06
     Griffith
    -0.06
     Soccer
    -0.06
     Mall
    -0.06
    ierte
    -0.06
    POSITIVE LOGITS
     betray
    0.08
    的地方
    0.07
     JV
    0.07
     origen
    0.06
     пис
    0.06
    ’daki
    0.06
    ної
    0.06
    dbcTemplate
    0.06
    _audio
    0.06
     JPEG
    0.06
    Act Density 0.048%

    No Known Activations