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

    Neuronpedia

    INDEX
    Explanations

    Avoiding negative outcomes (programming)

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    ô
    -0.07
    Officers
    -0.07
    くん
    -0.07
     Officers
    -0.07
    ま
    -0.07
     ounce
    -0.07
    >{!!
    -0.06
    よく
    -0.06
    ᗢ
    -0.06
    POSITIVE LOGITS
    -input
    0.08
     rut
    0.08
     difficult
    0.07
     edu
    0.07
    izont
    0.07
    .Remote
    0.06
     bare
    0.06
    )||
    0.06
    .bg
    0.06
     Commit
    0.06
    Act Density 0.135%

    No Known Activations