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

    Neuronpedia

    INDEX
    Explanations

    calibration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ignoring
    -0.06
    .Entry
    -0.06
    (seq
    -0.06
    larına
    -0.06
     últ
    -0.06
     varsa
    -0.06
    Please
    -0.06
     mContext
    -0.06
    Disposable
    -0.06
    Truth
    -0.06
    POSITIVE LOGITS
    �
    0.07
    urate
    0.07
     divine
    0.06
     вмі
    0.06
     listen
    0.06
    URED
    0.06
    IR
    0.06
    xon
    0.06
     Stockholm
    0.06
     troub
    0.06
    Act Density 0.003%

    No Known Activations