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

    Neuronpedia

    INDEX
    Explanations

    ABS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    暕
    -0.08
     Vet
    -0.07
    预算
    -0.07
     Milk
    -0.07
    最有
    -0.07
     ash
    -0.07
     č
    -0.06
    _lv
    -0.06
    电解
    -0.06
     Exhaust
    -0.06
    POSITIVE LOGITS
     לשנות
    0.07
     liberal
    0.07
    +'
    0.07
     Sel
    0.07
     distorted
    0.06
    urbed
    0.06
     alternatives
    0.06
     thing
    0.06
     violate
    0.06
    健康发展
    0.06
    Act Density 0.000%

    No Known Activations