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

    Neuronpedia

    INDEX
    Explanations

    Pokémon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     전혀
    -0.09
     Signature
    -0.07
    -that
    -0.07
    נים
    -0.07
    奔跑
    -0.07
     Diploma
    -0.07
     Symbols
    -0.07
    يم
    -0.07
     Fres
    -0.07
     וגם
    -0.07
    POSITIVE LOGITS
    consult
    0.07
    Runtime
    0.07
    Carol
    0.07
    按下
    0.07
    _sk
    0.06
    >');
↵
    0.06
    Unsafe
    0.06
    cpu
    0.06
    Visual
    0.06
    Deal
    0.06
    Act Density 0.016%

    No Known Activations