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

    Neuronpedia

    INDEX
    Explanations

    code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    樹
    -0.06
    ناء
    -0.06
    โรค
    -0.06
    �
    -0.06
     نقشه
    -0.06
     youths
    -0.06
    Remember
    -0.06
     dgv
    -0.06
    成员
    -0.06
    ']))↵↵
    -0.05
    POSITIVE LOGITS
     walnut
    0.07
     —
    0.07
    ordered
    0.07
     terr
    0.07
     실�
    0.06
    ával
    0.06
    해야
    0.06
     Lit
    0.06
    chein
    0.06
     GPLv
    0.06
    Act Density 0.101%

    No Known Activations