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

    Neuronpedia

    INDEX
    Explanations

    narcissism

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rlen
    -0.07
    ECTOR
    -0.07
    ями
    -0.07
     Alternate
    -0.06
    Ahead
    -0.06
     misleading
    -0.06
    POINTS
    -0.06
     Paths
    -0.06
    career
    -0.06
    	Matrix
    -0.06
    POSITIVE LOGITS
     ext
    0.07
     육
    0.07
    `='$
    0.07
     initWithFrame
    0.07
    Cadastro
    0.06
    �
    0.06
    0.06
     (_.
    0.06
     könnte
    0.06
     st
    0.06
    Act Density 0.083%

    No Known Activations