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

    Neuronpedia

    INDEX
    Explanations

    lean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Elk
    -0.08
    sprintf
    -0.07
    _LOOKUP
    -0.07
    dataset
    -0.07
     there
    -0.07
     Así
    -0.07
    sure
    -0.07
     Sugar
    -0.07
    Mot
    -0.07
    Lots
    -0.07
    POSITIVE LOGITS
     leaned
    0.08
     penchant
    0.08
    住房和城
    0.08
    CED
    0.07
    钢筋
    0.07
    혔
    0.07
    ﳜ
    0.07
    亭
    0.07
    ވ
    0.07
    -average
    0.07
    Act Density 0.005%

    No Known Activations