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

    Neuronpedia

    INDEX
    Explanations

    Quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pg
    -0.06
    ordova
    -0.06
     geliyor
    -0.06
    "]);
    -0.06
    .getSource
    -0.06
    ‌هایی
    -0.06
    ;:;:
    -0.06
     Doğum
    -0.06
    โ
    -0.06
     +/-
    -0.06
    POSITIVE LOGITS
    (entry
    0.07
    ields
    0.07
     cluster
    0.07
     mild
    0.07
     checked
    0.07
     Sell
    0.07
     suspect
    0.07
     FULL
    0.06
     manual
    0.06
    buff
    0.06
    Act Density 0.003%

    No Known Activations