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

    Neuronpedia

    INDEX
    Explanations

    environmentally

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    @a
    -0.07
    Partial
    -0.06
     Reeves
    -0.06
     secs
    -0.06
     cx
    -0.06
    �
    -0.06
    yx
    -0.05
     Os
    -0.05
    자
    -0.05
     axes
    -0.05
    POSITIVE LOGITS
     kadar
    0.08
     Manchester
    0.07
    ¯
    0.07
     changer
    0.07
     PodsDummy
    0.07
     whipping
    0.07
    킨
    0.07
    untime
    0.07
     Kullan
    0.07
     mission
    0.07
    Act Density 0.005%

    No Known Activations