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

    Neuronpedia

    INDEX
    Explanations

    secret

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GOLD
    -0.06
    	stack
    -0.06
    $m
    -0.06
    }},
    -0.06
    .A
    -0.06
     '-'
    -0.06
    _properties
    -0.06
    append
    -0.06
     Chill
    -0.06
     zombies
    -0.06
    POSITIVE LOGITS
    Never
    0.07
    ‌کننده
    0.07
     Memo
    0.07
    anyl
    0.07
    edor
    0.07
    Arizona
    0.06
     entitled
    0.06
     commit
    0.06
    ‌دان
    0.06
     liebe
    0.06
    Act Density 0.004%

    No Known Activations