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

    Neuronpedia

    INDEX
    Explanations

    long phrases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Browsable
    -0.07
    ерб
    -0.07
    抗
    -0.06
    -Year
    -0.06
    -cost
    -0.06
    ](↵
    -0.06
     Fauc
    -0.06
    $ret
    -0.06
    ensors
    -0.06
    .Iter
    -0.06
    POSITIVE LOGITS
     minden
    0.06
    *R
    0.06
     flagged
    0.06
     harmon
    0.06
     لی
    0.06
    }}}
    0.06
     sco
    0.06
     snad
    0.06
     defended
    0.06
     Эти
    0.06
    Act Density 0.124%

    No Known Activations