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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     correlate
    -0.07
     values
    -0.06
    ITES
    -0.06
     ser
    -0.06
     Zombie
    -0.06
    阵
    -0.06
     editing
    -0.06
    nim
    -0.06
     additions
    -0.06
    inned
    -0.06
    POSITIVE LOGITS
     yarar
    0.07
    _trees
    0.07
     گردش
    0.07
     καν
    0.06
     بیمه
    0.06
     fyz
    0.06
     подт
    0.06
    ps
    0.06
     LDL
    0.06
    ~,
    0.06
    Act Density 0.000%

    No Known Activations