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

    Neuronpedia

    INDEX
    Explanations

    Code/Technical definitions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ()↵↵
    -0.08
    ankan
    -0.07
    😤
    -0.07
     ,↵↵
    -0.07
    JI
    -0.07
    oru
    -0.07
    랸
    -0.07
     analyzed
    -0.07
    (tok
    -0.07
    ,,
    -0.07
    POSITIVE LOGITS
     �
    0.08
     �
    0.07
     Device
    0.07
    cascade
    0.07
    Soft
    0.07
     ferr
    0.07
     dou
    0.07
     numer
    0.07
     numeral
    0.07
     soft
    0.07
    Act Density 0.068%

    No Known Activations