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

    Neuronpedia

    INDEX
    Explanations

    send

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itelist
    -0.07
     Rust
    -0.07
    .BUTTON
    -0.07
    .rank
    -0.07
    .observe
    -0.07
     Pure
    -0.07
     смеш
    -0.07
     sürdür
    -0.06
     surprising
    -0.06
     rů
    -0.06
    POSITIVE LOGITS
    �
    0.07
     ANT
    0.06
    QUIRE
    0.06
    CLUDE
    0.06
     یکی
    0.06
    stellen
    0.06
    objectManager
    0.06
    кта
    0.06
    jvu
    0.06
     Nir
    0.06
    Act Density 0.017%

    No Known Activations