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

    Neuronpedia

    INDEX
    Explanations

    math derivations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     רבים
    -0.08
     Butler
    -0.08
    oloj
    -0.08
    whatever
    -0.08
     ple
    -0.08
    okuv
    -0.08
     атмосфер
    -0.07
     infatti
    -0.07
     rope
    -0.07
     hizi
    -0.07
    POSITIVE LOGITS
     ----------------
    0.08
    **↵↵
    0.08
    ***↵↵
    0.08
     Relevant
    0.08
     ###↵
    0.08
    **↵
    0.08
     Needed
    0.08
     ****************
    0.07
     통한
    0.07
     Different
    0.07
    Act Density 0.045%

    No Known Activations