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

    Neuronpedia

    INDEX
    Explanations

    020

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    〕
    -0.07
    가
    -0.06
     벌
    -0.06
    iều
    -0.06
    fecha
    -0.06
     verd
    -0.06
    bero
    -0.06
     pode
    -0.06
    록
    -0.06
    elope
    -0.06
    POSITIVE LOGITS
    Moved
    0.06
    _idxs
    0.06
     Stranger
    0.06
    _VECTOR
    0.06
    Allowed
    0.06
     countert
    0.06
    =localhost
    0.06
     focusing
    0.06
     French
    0.06
    mur
    0.06
    Act Density 0.005%

    No Known Activations