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

    Neuronpedia

    INDEX
    Explanations

    mermaid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .*)
    -0.07
    .Part
    -0.07
    iliar
    -0.06
     Ellison
    -0.06
     đặt
    -0.06
    ikal
    -0.06
     código
    -0.06
     thuê
    -0.06
     щось
    -0.06
     Beitrag
    -0.06
    POSITIVE LOGITS
    maids
    0.08
    mer
    0.08
    �
    0.06
     ]↵↵↵
    0.06
    promise
    0.06
     Neptune
    0.06
     human
    0.06
     bubb
    0.06
    }")]↵
    0.06
    `↵
    0.06
    Act Density 0.003%

    No Known Activations