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

    Neuronpedia

    INDEX
    Explanations

    reason

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    к
    -0.07
     MSP
    -0.07
    metic
    -0.07
     adult
    -0.06
    顔
    -0.06
    哪
    -0.06
    北
    -0.06
    Tpl
    -0.06
    _available
    -0.06
     bitterness
    -0.06
    POSITIVE LOGITS
     zug
    0.07
    Sac
    0.07
     ταιν
    0.06
     evid
    0.06
     podpor
    0.06
     halluc
    0.06
    .Low
    0.06
     �
    0.06
     enlight
    0.06
    OnClickListener
    0.06
    Act Density 0.041%

    No Known Activations