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

    Neuronpedia

    INDEX
    Explanations

    Perhaps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    __':
    -0.89
    __":
    -0.65
     pewno
    -0.63
    ControllerAdvice
    -0.63
    __':
    -0.60
     abandonné
    -0.60
    Viitteet
    -0.57
    posedge
    -0.56
    ungkin
    -0.56
     regardé
    -0.55
    POSITIVE LOGITS
    ѝ
    0.57
     both
    0.56
     tanto
    0.51
     several
    0.49
     it
    0.48
    HideFlags
    0.47
    PMailer
    0.45
    postValue
    0.45
    both
    0.43
     neither
    0.42
    Act Density 0.014%

    No Known Activations