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

    Neuronpedia

    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cleanup
    -0.07
    .fragment
    -0.07
     Госп
    -0.06
     Logger
    -0.06
     öl
    -0.06
    	It
    -0.06
    ably
    -0.06
    ्ट
    -0.06
    !”↵↵
    -0.06
     col
    -0.06
    POSITIVE LOGITS
    확
    0.07
     personn
    0.06
    ,callback
    0.06
    WX
    0.06
    force
    0.06
    vail
    0.06
     reins
    0.06
     enact
    0.06
     آم
    0.06
     sesión
    0.06
    Act Density 0.000%

    No Known Activations