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

    Neuronpedia

    INDEX
    Explanations

    tier

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    handleChange
    -0.07
     Love
    -0.07
    _MAY
    -0.07
    objs
    -0.07
    例如
    -0.06
    (["
    -0.06
    antha
    -0.06
     نموده
    -0.06
     下午
    -0.06
     †
    -0.06
    POSITIVE LOGITS
     tier
    0.11
    -tier
    0.09
     Tier
    0.09
     tiers
    0.08
    trim
    0.07
     AA
    0.07
    roid
    0.07
    _ATOMIC
    0.07
     firm
    0.07
     licensors
    0.07
    Act Density 0.002%

    No Known Activations