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

    Neuronpedia

    INDEX
    Explanations

    isolation or sickness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     based
    -0.07
     住
    -0.06
     منتشر
    -0.06
    .connections
    -0.06
    _load
    -0.06
    Deep
    -0.06
    	frame
    -0.06
     "↵
    -0.06
    _abstract
    -0.06
    INCREMENT
    -0.06
    POSITIVE LOGITS
    irting
    0.07
     declare
    0.07
     Nonetheless
    0.07
    ιας
    0.07
    :expr
    0.06
    들의
    0.06
    CellStyle
    0.06
     ragaz
    0.06
     Talking
    0.06
     declaring
    0.06
    Act Density 0.158%

    No Known Activations