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

    Neuronpedia

    INDEX
    Explanations

    say "the"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	td
    -0.07
    (rand
    -0.06
     Switch
    -0.06
     Higgins
    -0.06
    rxjs
    -0.06
     Roe
    -0.06
     Silence
    -0.06
    brates
    -0.06
     componentWillUnmount
    -0.06
    	flag
    -0.06
    POSITIVE LOGITS
    _LS
    0.07
     hoş
    0.07
    GOOD
    0.06
     snaží
    0.06
    BUF
    0.06
    ABI
    0.06
    ویه
    0.06
    heard
    0.06
     z
    0.06
    ´:
    0.06
    Act Density 0.012%

    No Known Activations