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

    Neuronpedia

    INDEX
    Explanations

    Temporal words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sinks
    -0.07
     такими
    -0.07
    -С
    -0.07
     کسب
    -0.07
     nas
    -0.07
     Ko
    -0.06
     Ödül
    -0.06
    �
    -0.06
    )L
    -0.06
    گری
    -0.06
    POSITIVE LOGITS
     #↵
    0.06
     suffice
    0.06
    .light
    0.06
    locks
    0.06
    (equal
    0.06
     employment
    0.06
    (mock
    0.06
     öld
    0.06
    .skill
    0.06
    .Since
    0.06
    Act Density 0.102%

    No Known Activations