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

    Neuronpedia

    INDEX
    Explanations

    various

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,s
    -0.07
     Trie
    -0.07
    Attack
    -0.06
    .Add
    -0.06
    ,d
    -0.06
    .Created
    -0.06
    .setTextSize
    -0.06
     rho
    -0.06
    ывал
    -0.06
     ฟร
    -0.06
    POSITIVE LOGITS
     proced
    0.07
    แจ
    0.07
     administrators
    0.06
    ModelCreating
    0.06
     insights
    0.06
     populations
    0.06
     sắc
    0.06
    endoza
    0.06
     Proposition
    0.06
     Jonas
    0.06
    Act Density 0.003%

    No Known Activations