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

    Neuronpedia

    INDEX
    Explanations

    Phone numbers and addresses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    坌
    -0.07
     Jarvis
    -0.07
     ignoring
    -0.07
    𝒜
    -0.07
    ()(
    -0.07
    _LABEL
    -0.07
    LEY
    -0.07
     fibers
    -0.07
     emailed
    -0.06
     Liberals
    -0.06
    POSITIVE LOGITS
    vf
    0.07
    udit
    0.07
     WIN
    0.07
    	win
    0.07
     Hag
    0.06
    日常
    0.06
    .firebase
    0.06
    שולח
    0.06
     times
    0.06
    常说
    0.06
    Act Density 0.005%

    No Known Activations