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

    Neuronpedia

    INDEX
    Explanations

    letters and correspondence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    当之
    -0.07
     Instances
    -0.07
     resist
    -0.07
    餐厅
    -0.07
     spins
    -0.07
     crushing
    -0.07
     IST
    -0.06
     starring
    -0.06
     foremost
    -0.06
     repe
    -0.06
    POSITIVE LOGITS
    '''↵↵
    0.08
    aterial
    0.07
    🕝
    0.07
    #from
    0.07
    cob
    0.07
     acept
    0.06
    lic
    0.06
    hua
    0.06
    .tb
    0.06
    حاول
    0.06
    Act Density 0.010%

    No Known Activations