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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .multi
    -0.07
     uden
    -0.07
    .Scheme
    -0.07
     Directive
    -0.06
     бізнес
    -0.06
    ющихся
    -0.06
     volatility
    -0.06
    })
↵
↵
    -0.06
     small
    -0.06
    筑
    -0.06
    POSITIVE LOGITS
     combust
    0.07
    arged
    0.06
     stabbing
    0.06
    override
    0.06
    (copy
    0.06
     hairy
    0.06
    _SEL
    0.06
    dealloc
    0.06
    uka
    0.06
     stemming
    0.06
    Act Density 0.181%

    No Known Activations