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

    Neuronpedia

    INDEX
    Explanations

    "as" for duration/scaling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Command
    -0.07
    	range
    -0.07
     спрос
    -0.07
     intensified
    -0.06
    hof
    -0.06
    اج
    -0.06
     ROM
    -0.06
     politics
    -0.06
    _verts
    -0.06
     jpeg
    -0.06
    POSITIVE LOGITS
    ห
    0.07
     Beast
    0.07
    邮箱
    0.07
    _unused
    0.06
     cuerpo
    0.06
    τι
    0.06
     الوطني
    0.06
    割
    0.06
    ")){
↵
    0.06
     //↵
    0.06
    Act Density 0.015%

    No Known Activations