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

    Neuronpedia

    INDEX
    Explanations

    undesirable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    show
    -0.07
     Adults
    -0.07
     Aim
    -0.07
    aws
    -0.06
    _wrong
    -0.06
     chilled
    -0.06
     steadily
    -0.06
    Finite
    -0.06
     taps
    -0.06
     неп
    -0.06
    POSITIVE LOGITS
     undesirable
    0.32
    irable
    0.09
     unpleasant
    0.07
    DEL
    0.07
     undes
    0.07
     stressing
    0.06
    tempt
    0.06
    	ex
    0.06
     MS
    0.06
     Стар
    0.06
    Act Density 0.003%

    No Known Activations