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

    Neuronpedia

    INDEX
    Explanations

    201

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Centers
    -0.07
    .pageX
    -0.06
     Replica
    -0.06
    ikit
    -0.06
     shit
    -0.06
     corrobor
    -0.06
     Meat
    -0.06
    _BLEND
    -0.06
    enerate
    -0.06
    .document
    -0.06
    POSITIVE LOGITS
    ilen
    0.07
    emperature
    0.06
     showcased
    0.06
     fase
    0.06
     enjoyed
    0.06
     otra
    0.06
     около
    0.06
     ;↵
    0.06
    ícul
    0.06
    edii
    0.06
    Act Density 0.024%

    No Known Activations