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

    Neuronpedia

    INDEX
    Explanations

    learn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /sub
    -0.06
    نج
    -0.06
    -inline
    -0.06
    USB
    -0.06
    .spacing
    -0.06
     згад
    -0.06
    Inserted
    -0.06
     stir
    -0.06
     "'.$
    -0.06
    Tonight
    -0.06
    POSITIVE LOGITS
    eds
    0.07
    _invite
    0.07
    hardt
    0.07
    ehir
    0.06
     hist
    0.06
    delivery
    0.06
    ja
    0.06
     akıl
    0.06
    (expr
    0.06
     Recall
    0.06
    Act Density 0.000%

    No Known Activations