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

    Neuronpedia

    INDEX
    Explanations

    learning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pastor
    -0.07
     anlamına
    -0.07
    breadcrumb
    -0.06
    Oper
    -0.06
     أح
    -0.06
    ної
    -0.06
    fk
    -0.06
    Visitor
    -0.06
    (conv
    -0.06
    .fromString
    -0.06
    POSITIVE LOGITS
      	↵
    0.06
     /[
    0.06
    wife
    0.06
     �
    0.06
     Neither
    0.06
                                            ↵
    0.06
     Each
    0.06
     Lawyer
    0.06
    du
    0.06
    Ads
    0.06
    Act Density 0.043%

    No Known Activations