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

    Neuronpedia

    INDEX
    Explanations

    Sensory descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arsity
    -0.07
    parameters
    -0.07
    ひ
    -0.06
    elts
    -0.06
     Hands
    -0.06
    rikes
    -0.06
    (ob
    -0.06
    adium
    -0.06
    -0.06
    oid
    -0.06
    POSITIVE LOGITS
    ША
    0.07
    Woman
    0.07
    诊
    0.07
    �
    0.06
    _issues
    0.06
     brib
    0.06
    Copying
    0.06
    .hand
    0.06
     Seamless
    0.06
    ográf
    0.06
    Act Density 0.056%

    No Known Activations