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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $db
    -0.06
    曲
    -0.06
    .spacing
    -0.06
     kettle
    -0.06
     bao
    -0.06
    (P
    -0.06
    etooth
    -0.06
     remarkably
    -0.06
     nada
    -0.06
    lerine
    -0.06
    POSITIVE LOGITS
     Muscle
    0.07
     vanilla
    0.06
    로그
    0.06
    _SIM
    0.06
     generic
    0.06
    }
↵
    0.06
     âm
    0.06
     softer
    0.06
     navy
    0.06
    consistent
    0.06
    Act Density 0.001%

    No Known Activations