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

    Neuronpedia

    INDEX
    Explanations

    asm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prototypes
    -0.08
     fully
    -0.07
     Yug
    -0.07
    拜
    -0.06
    ellt
    -0.06
     moving
    -0.06
    .Logging
    -0.06
     centrally
    -0.06
    628
    -0.06
     Thanksgiving
    -0.06
    POSITIVE LOGITS
    plete
    0.08
    ymbol
    0.07
    (".");↵
    0.07
    олом
    0.07
    Explanation
    0.07
    UBLE
    0.07
    UND
    0.07
    ughter
    0.07
    стика
    0.07
    籍
    0.06
    Act Density 0.004%

    No Known Activations