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

    Neuronpedia

    INDEX
    Explanations

    Programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    復
    -0.28
    å¤į
    -0.27
    ôle
    -0.27
     backs
    -0.26
    Ton
    -0.26
    <class
    -0.25
    è¾ĪåŃIJ
    -0.25
    typeof
    -0.25
    esimal
    -0.24
    对å¾ħ
    -0.24
    POSITIVE LOGITS
    examples
    0.33
     Examples
    0.31
     FAQs
    0.31
    Examples
    0.29
     Opposition
    0.27
    ãĤ¬ãĤ¤ãĥī
    0.26
    owner
    0.26
     Owner
    0.26
     Maintain
    0.26
     examples
    0.25
    Act Density 0.076%

    No Known Activations