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

    Neuronpedia

    INDEX
    Explanations

    "

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    される
    -0.07
     вы
    -0.07
    hur
    -0.07
    童
    -0.07
    (&_
    -0.07
     й
    -0.07
     healthy
    -0.06
     intentional
    -0.06
     Voldemort
    -0.06
     ל
    -0.06
    POSITIVE LOGITS
    (hw
    0.07
    _RST
    0.07
    .boolean
    0.07
    jandro
    0.06
    alarm
    0.06
    ")){↵
    0.06
    $form
    0.06
                    
    0.06
     recruiters
    0.06
     allergies
    0.06
    Act Density 0.020%

    No Known Activations