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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SYS
    -0.07
    .with
    -0.07
     PropelException
    -0.07
     науч
    -0.07
    饹
    -0.07
     développement
    -0.07
    演变
    -0.07
     NOW
    -0.06
    𝖊
    -0.06
    汈
    -0.06
    POSITIVE LOGITS
    >Password
    0.07
    (thing
    0.07
     parms
    0.07
    (span
    0.07
     qualifier
    0.07
    reject
    0.07
     Remaining
    0.06
     Terminator
    0.06
    	children
    0.06
    _KERNEL
    0.06
    Act Density 0.000%

    No Known Activations