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

    Neuronpedia

    INDEX
    Explanations

    desperate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unicode
    -0.06
    됨
    -0.06
    (instance
    -0.06
     ή
    -0.06
     развития
    -0.06
     llvm
    -0.06
    _com
    -0.06
     Giov
    -0.06
    _Tag
    -0.06
     Pru
    -0.06
    POSITIVE LOGITS
    脱
    0.07
    nesota
    0.07
     francouz
    0.07
    AD
    0.07
     desperate
    0.07
    teri
    0.07
    adu
    0.07
    rece
    0.06
    jišť
    0.06
    comp
    0.06
    Act Density 0.004%

    No Known Activations