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

    Neuronpedia

    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igrams
    -0.07
    waters
    -0.07
    moth
    -0.06
    τογραφ
    -0.06
    alarm
    -0.06
    ologické
    -0.06
    mites
    -0.06
     structure
    -0.06
    ometers
    -0.06
    acies
    -0.06
    POSITIVE LOGITS
    .insert
    0.07
    _nf
    0.07
    роз
    0.06
     phòng
    0.06
    dirname
    0.06
    δε
    0.06
    ี้
    0.06
    itmap
    0.06
    ecektir
    0.06
    かな
    0.06
    Act Density 0.008%

    No Known Activations