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

    Neuronpedia

    INDEX
    Explanations

    cache

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     guards
    -0.08
     ={↵
    -0.07
    裾
    -0.07
     TOUR
    -0.07
    肠胃
    -0.07
    NW
    -0.07
    _TRA
    -0.07
     Houses
    -0.06
     completamente
    -0.06
    Model
    -0.06
    POSITIVE LOGITS
    _mtime
    0.08
     defamation
    0.07
    🦠
    0.07
    ifact
    0.07
     fasta
    0.07
    🎊
    0.07
    翃
    0.07
     oxide
    0.07
    ₠
    0.07
    foy
    0.07
    Act Density 0.006%

    No Known Activations