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

    Neuronpedia

    INDEX
    Explanations

    light or particle beams

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    تل
    -0.07
     atr
    -0.07
     respond
    -0.07
     landmarks
    -0.07
     drinking
    -0.07
     NGO
    -0.06
     tables
    -0.06
     Nguyen
    -0.06
     commands
    -0.06
     recording
    -0.06
    POSITIVE LOGITS
     diferencia
    0.07
    /se
    0.06
    /s
    0.06
     баг
    0.06
     "><
    0.06
    /")↵
    0.06
    TF
    0.06
    ��
    0.06
    ("/")↵
    0.06
     Поч
    0.06
    Act Density 0.037%

    No Known Activations