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

    Neuronpedia

    INDEX
    Explanations

    Code, logs, reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     equipo
    -0.07
     enjo
    -0.07
     muht
    -0.06
    medi
    -0.06
    苹果
    -0.06
     müz
    -0.06
    เจ
    -0.06
    .targets
    -0.06
     Kurds
    -0.06
     οι
    -0.06
    POSITIVE LOGITS
    hints
    0.07
    angs
    0.07
    					↵					↵
    0.06
    feedback
    0.06
    departureday
    0.06
     hangs
    0.06
    .transition
    0.06
    asis
    0.06
    ैग
    0.06
    ┘
    0.06
    Act Density 0.000%

    No Known Activations