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

    Neuronpedia

    INDEX
    Explanations

    here

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sang
    -0.07
    Ping
    -0.06
     Cleans
    -0.06
     nacional
    -0.06
     Medal
    -0.06
     professionnel
    -0.06
     кирп
    -0.06
     وأ
    -0.06
     TY
    -0.06
    usahaan
    -0.06
    POSITIVE LOGITS
     physiological
    0.07
    .Unity
    0.07
    BagConstraints
    0.06
    _sin
    0.06
     boring
    0.06
    Ÿ
    0.06
    .agent
    0.06
    _FM
    0.06
     contingency
    0.06
    PostBack
    0.06
    Act Density 0.012%

    No Known Activations