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

    Neuronpedia

    INDEX
    Explanations

    may

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chemical
    -0.07
     toward
    -0.07
     Killing
    -0.07
     editor
    -0.07
    Charlie
    -0.07
    Bill
    -0.07
     könnte
    -0.06
     Infinite
    -0.06
    Frank
    -0.06
     Hart
    -0.06
    POSITIVE LOGITS
     xhttp
    0.07
    .Msg
    0.07
     hava
    0.06
    _minutes
    0.06
     ryb
    0.06
    uguay
    0.06
    ЮЛ
    0.06
    (signal
    0.06
     Pep
    0.06
    (Main
    0.06
    Act Density 0.001%

    No Known Activations