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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _surface
    -0.07
     а
    -0.07
    	Connection
    -0.07
     suicidal
    -0.07
     FreeBSD
    -0.07
    .learn
    -0.07
    &S
    -0.07
    <boolean
    -0.07
     설치
    -0.06
     forme
    -0.06
    POSITIVE LOGITS
    */↵
    0.06
    whole
    0.06
    IDO
    0.06
     conscient
    0.06
    iterr
    0.06
    RO
    0.06
     fired
    0.06
    alette
    0.06
    ido
    0.06
     roughly
    0.06
    Act Density 0.018%

    No Known Activations