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

    Neuronpedia

    INDEX
    Explanations

    Occult and esoteric knowledge

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Drama
    -0.07
    نة
    -0.07
    ่อต
    -0.07
    -cycle
    -0.07
    สำเร
    -0.07
    ोन
    -0.06
     свід
    -0.06
    REM
    -0.06
    -------------
    -0.06
    ียด
    -0.06
    POSITIVE LOGITS
     Protector
    0.07
     особ
    0.07
     Πανεπ
    0.06
    idla
    0.06
     yum
    0.06
    .Network
    0.06
     Foo
    0.06
     Fors
    0.06
     Wholesale
    0.05
     Pap
    0.05
    Act Density 0.034%

    No Known Activations