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

    Neuronpedia

    INDEX
    Explanations

    code assignment or variable names like `field` and `this`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    []={
    -1.12
    thmus
    -1.10
    ,\,
    -1.09
    🫴
    -1.04
    bestos
    -1.03
    bited
    -1.02
    apnews
    -1.02
    回到了
    -1.01
    maining
    -1.00
    cleos
    -1.00
    POSITIVE LOGITS
     =
    1.81
    }=\
    1.09
    set
    1.06
    jenigen
    1.06
    }=
    1.05
     one
    1.04
     will
    1.02
     =\
    1.02
    块钱
    0.99
    >=</
    0.98
    Act Density 0.001%

    No Known Activations