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

    Neuronpedia

    INDEX
    Explanations

    bas/basal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     muchas
    -0.06
     todas
    -0.06
    Numbers
    -0.06
    nowledge
    -0.06
     Ade
    -0.06
    なんて
    -0.06
    nehmer
    -0.06
     fierce
    -0.06
     veil
    -0.06
    frica
    -0.06
    POSITIVE LOGITS
     Basin
    0.09
     basin
    0.08
     basically
    0.07
    .son
    0.07
    基
    0.07
     Abdul
    0.07
     Bill
    0.07
    며
    0.07
     základ
    0.07
    065
    0.07
    Act Density 0.014%

    No Known Activations