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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prosecutions
    -0.07
     Bootstrap
    -0.06
     development
    -0.06
     pontos
    -0.06
    ``↵
    -0.06
     facet
    -0.06
     tread
    -0.06
     pot
    -0.06
    ुमत
    -0.06
     Ob
    -0.06
    POSITIVE LOGITS
    abor
    0.06
    .EX
    0.06
     thịt
    0.06
    thood
    0.06
    lodash
    0.06
    xed
    0.06
    Ping
    0.06
    Ess
    0.06
    تی
    0.05
    نسا
    0.05
    Act Density 0.043%

    No Known Activations