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

    Neuronpedia

    INDEX
    Explanations

    java

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $temp
    -0.06
     graphic
    -0.06
    щими
    -0.06
     installation
    -0.06
    }?
    -0.06
    出品者
    -0.06
     stout
    -0.06
    _Show
    -0.06
    ]].
    -0.06
    istributions
    -0.06
    POSITIVE LOGITS
     revoked
    0.07
     CRE
    0.06
    ffa
    0.06
     banka
    0.06
    estic
    0.06
     شبکه
    0.06
     Das
    0.06
     fark
    0.06
     MAY
    0.06
     Math
    0.06
    Act Density 0.002%

    No Known Activations