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

    Neuronpedia

    INDEX
    Explanations

    here

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .sms
    -0.07
    (pass
    -0.07
     thirteen
    -0.07
     nf
    -0.07
     لي
    -0.06
    updates
    -0.06
    .search
    -0.06
     nrw
    -0.06
     nt
    -0.06
     CW
    -0.06
    POSITIVE LOGITS
    pheres
    0.07
     bied
    0.07
    _K
    0.07
    oire
    0.07
    دم
    0.07
    =False
    0.06
    Faces
    0.06
     cylinders
    0.06
    _phi
    0.06
    iances
    0.06
    Act Density 0.007%

    No Known Activations