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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -scripts
    -0.06
     humility
    -0.06
    ск
    -0.06
     seperti
    -0.06
    �
    -0.06
    SMTP
    -0.06
     lastname
    -0.06
    msg
    -0.06
    .nt
    -0.06
    _prior
    -0.06
    POSITIVE LOGITS
    PLETED
    0.07
     Picasso
    0.07
     머
    0.07
     applauded
    0.07
    负
    0.06
    uc
    0.06
     Summers
    0.06
     mathematical
    0.06
     admission
    0.06
    .cos
    0.06
    Act Density 0.035%

    No Known Activations