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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RATE
    -0.07
     comparative
    -0.07
    �ng
    -0.07
    urbation
    -0.07
    \Container
    -0.06
     pathways
    -0.06
    kiego
    -0.06
    -ag
    -0.06
     other
    -0.06
    G
    -0.06
    POSITIVE LOGITS
    move
    0.06
     обра
    0.06
     Rockies
    0.06
     Weber
    0.06
    ْف
    0.06
    _skill
    0.06
    ollower
    0.06
    PLATFORM
    0.06
     �
    0.06
    ÃO
    0.06
    Act Density 0.008%

    No Known Activations