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

    Neuronpedia

    INDEX
    Explanations

    Dashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Curso
    -0.07
    ρή
    -0.07
    abcdef
    -0.06
    ันย
    -0.06
    (comm
    -0.06
    spotify
    -0.06
     kuvvet
    -0.06
    .Magic
    -0.06
    Partner
    -0.06
    ITIVE
    -0.06
    POSITIVE LOGITS
     Opera
    0.07
    овер
    0.07
    Н
    0.06
     получ
    0.06
     obsession
    0.06
    Wa
    0.06
     disturbance
    0.06
     Wa
    0.06
     Wait
    0.06
    '>↵
    0.06
    Act Density 0.006%

    No Known Activations