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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    řad
    -0.07
     uppercase
    -0.06
     Suff
    -0.06
    acency
    -0.06
     readable
    -0.06
    Judge
    -0.06
     Samoa
    -0.06
     suf
    -0.06
    자인
    -0.06
     Prints
    -0.06
    POSITIVE LOGITS
     exempl
    0.07
    -pe
    0.06
     overnight
    0.06
     Larger
    0.06
    .grey
    0.06
    (diff
    0.06
    كه
    0.06
    lcd
    0.06
     newState
    0.06
     hinge
    0.06
    Act Density 0.001%

    No Known Activations