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

    Neuronpedia

    INDEX
    Explanations

    home

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ством
    -0.07
     یافته
    -0.07
     parece
    -0.07
     computation
    -0.07
    .od
    -0.07
     خارجية
    -0.07
     coats
    -0.07
    須
    -0.06
    actions
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    SenderId
    0.07
     aff
    0.06
     booth
    0.06
     Advoc
    0.06
     ach
    0.06
    ::/
    0.06
     svat
    0.06
    'nde
    0.06
     thi
    0.06
     DCHECK
    0.05
    Act Density 0.022%

    No Known Activations