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

    Neuronpedia

    INDEX
    Explanations

    loss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ъек
    -0.07
    woke
    -0.06
    Semaphore
    -0.06
    .country
    -0.06
    agan
    -0.06
     scream
    -0.06
     prisoner
    -0.06
    جی
    -0.06
    중에
    -0.06
    Emily
    -0.06
    POSITIVE LOGITS
    0.07
    +)
    0.07
     Description
    0.06
    错
    0.06
     insiders
    0.06
     SHR
    0.06
    cling
    0.06
    RATION
    0.06
    organisation
    0.06
    0.06
    Act Density 0.003%

    No Known Activations