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

    Neuronpedia

    INDEX
    Explanations

    they

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vens
    -0.07
     medios
    -0.07
    .ne
    -0.06
    赖
    -0.06
     техніч
    -0.06
    =sc
    -0.06
     constructive
    -0.06
    자기
    -0.06
    _env
    -0.06
    .bridge
    -0.06
    POSITIVE LOGITS
     Contr
    0.07
     Witnesses
    0.07
    statement
    0.06
    ifies
    0.06
    many
    0.06
    ैं।
    0.06
     equip
    0.06
    egas
    0.06
    imler
    0.06
     Callback
    0.06
    Act Density 0.000%

    No Known Activations