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

    Neuronpedia

    INDEX
    Explanations

    School grades

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     buscar
    -0.08
     buzz
    -0.07
     American
    -0.07
    st
    -0.07
     aliases
    -0.07
    ɔ
    -0.07
     initiative
    -0.07
    ǎ
    -0.07
    各县
    -0.07
     Gather
    -0.07
    POSITIVE LOGITS
    .getDay
    0.07
     heroin
    0.07
     pictured
    0.07
    著
    0.07
    [code
    0.06
    ┘
    0.06
     Hv
    0.06
     .'
    0.06
    .""
    0.06
    (force
    0.06
    Act Density 0.013%

    No Known Activations