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

    Neuronpedia

    INDEX
    Explanations

    Language models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reimb
    -0.10
    .AD
    -0.09
     trafficking
    -0.08
     crusher
    -0.08
     reimbursement
    -0.08
     pouch
    -0.08
     piste
    -0.08
     opat
    -0.08
     waived
    -0.08
     marketplace
    -0.08
    POSITIVE LOGITS
     tokenizer
    0.09
     predicting
    0.09
     cumul
    0.08
     generación
    0.08
    续
    0.08
     vorher
    0.08
     continuation
    0.08
    串
    0.08
     autore
    0.08
     генера
    0.08
    Act Density 0.011%

    No Known Activations