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

    Neuronpedia

    INDEX
    Explanations

    Online chat messages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     стоит
    -0.06
    _extend
    -0.06
    =%.
    -0.06
    르는
    -0.06
    �i
    -0.06
     já
    -0.06
    ungkin
    -0.06
    :'.$
    -0.06
    _TO
    -0.06
    _APPRO
    -0.06
    POSITIVE LOGITS
     episode
    0.07
     ké
    0.07
    .APP
    0.07
    سانی
    0.07
    оні
    0.06
    _sun
    0.06
    _VAR
    0.06
    	resolve
    0.06
    /gr
    0.06
     civilian
    0.06
    Act Density 0.037%

    No Known Activations