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

    Neuronpedia

    INDEX
    Explanations

    hit

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tradition
    -0.08
     מבוס
    -0.07
    _on
    -0.07
    rtle
    -0.07
     Dy
    -0.06
     esl
    -0.06
    ╩
    -0.06
     rg
    -0.06
    older
    -0.06
    甬
    -0.06
    POSITIVE LOGITS
     honest
    0.07
    ="#
    0.07
    aternion
    0.07
    successful
    0.07
     Kaz
    0.07
     updates
    0.07
    IPP
    0.07
    .Array
    0.07
     pointless
    0.06
    ]interface
    0.06
    Act Density 0.022%

    No Known Activations