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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /New
    -0.08
    .What
    -0.07
    .INVALID
    -0.07
    Sal
    -0.07
    ält
    -0.07
     bite
    -0.07
    ﰞ
    -0.07
    (){}↵↵
    -0.07
     jemand
    -0.06
    zł
    -0.06
    POSITIVE LOGITS
     acres
    0.08
     CONNECTION
    0.07
    相继
    0.07
     conhec
    0.07
     Telescope
    0.07
    -written
    0.07
     Objects
    0.07
    ROOT
    0.07
    보고
    0.06
    𒌨
    0.06
    Act Density 0.004%

    No Known Activations