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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ;k
    -0.06
    ,on
    -0.06
    _il
    -0.06
     uk
    -0.06
     zen
    -0.06
    दम
    -0.06
     OEM
    -0.06
     só
    -0.06
    nosis
    -0.06
     vznik
    -0.06
    POSITIVE LOGITS
    wit
    0.07
    Guess
    0.07
    numerusform
    0.06
     lange
    0.06
     vedere
    0.06
     Guth
    0.06
    unnable
    0.06
    rompt
    0.06
     twilight
    0.06
    bel
    0.06
    Act Density 0.005%

    No Known Activations