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

    Neuronpedia

    INDEX
    Explanations

    code/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     và
    -0.07
     isol
    -0.06
     usage
    -0.06
    .some
    -0.06
     over
    -0.06
     proto
    -0.06
     limited
    -0.06
    ому
    -0.06
     Using
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     KD
    0.08
     Nicaragua
    0.07
     тисяч
    0.07
    _DURATION
    0.07
     دانش
    0.06
     Grape
    0.06
    ADMIN
    0.06
     Tet
    0.06
     stere
    0.06
    Thousands
    0.06
    Act Density 0.000%

    No Known Activations