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

    Neuronpedia

    INDEX
    Explanations

    Conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ifference
    -0.07
    �
    -0.06
    ifferences
    -0.06
     funk
    -0.06
    ву
    -0.06
     kişisel
    -0.06
     Sinh
    -0.06
    sprite
    -0.06
    씩
    -0.06
     خاطر
    -0.06
    POSITIVE LOGITS
     told
    0.06
     }*/↵
    0.06
     `;↵
    0.06
     농
    0.06
     };
↵
    0.06
     hend
    0.06
    ))));↵
    0.06
    /user
    0.06
    vert
    0.06
    --}}↵
    0.06
    Act Density 0.051%

    No Known Activations