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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Interrupt
    -0.07
    Ṗ
    -0.07
    (fullfile
    -0.07
    ∅
    -0.07
     volupt
    -0.07
     Windows
    -0.07
     שיכול
    -0.06
     rollback
    -0.06
    ddb
    -0.06
    /work
    -0.06
    POSITIVE LOGITS
    خيارات
    0.07
    唱片
    0.07
     encontrado
    0.07
    VR
    0.07
    燕
    0.07
    CG
    0.07
     IDS
    0.07
    鳝
    0.06
    RSS
    0.06
     ahora
    0.06
    Act Density 0.046%

    No Known Activations