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

    Neuronpedia

    INDEX
    Explanations

    Mathematical formulas, code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ruins
    -0.07
    uctor
    -0.07
    ious
    -0.06
     overwhelmingly
    -0.06
    τησε
    -0.06
    arLayout
    -0.06
    emoth
    -0.06
    urrent
    -0.06
    entes
    -0.06
    ozem
    -0.06
    POSITIVE LOGITS
     }?>↵
    0.06
     GB
    0.06
    도가
    0.06
    ])↵↵↵
    0.06
    ?"↵↵
    0.06
    )))↵↵↵
    0.06
    행
    0.06
    '↵↵↵
    0.06
    }

↵
    0.06
     CR
    0.06
    Act Density 0.009%

    No Known Activations