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

    Neuronpedia

    INDEX
    Explanations

    warnings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     irgend
    -0.07
     cherche
    -0.07
     받
    -0.06
     Ρ
    -0.06
    を受
    -0.06
    -0.06
    53
    -0.06
    考え
    -0.06
    ��
    -0.06
    เตร
    -0.06
    POSITIVE LOGITS
    AMAGE
    0.06
    ]=-
    0.06
    gregated
    0.06
     هش
    0.06
    fila
    0.06
    ++]=
    0.06
    Jud
    0.06
    Warning
    0.06
     hız
    0.06
     �
    0.06
    Act Density 0.018%

    No Known Activations