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

    Neuronpedia

    INDEX
    Explanations

    notated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    matchCondition
    -0.79
     ComVisible
    -0.64
    fjspx
    -0.64
     betweenstory
    -0.61
    npos
    -0.60
    TERY
    -0.60
    வும்
    -0.60
     utafitiHapana
    -0.59
    pushFollow
    -0.59
    WriteLiteral
    -0.59
    POSITIVE LOGITS
     bibliography
    0.51
     bibliographies
    0.50
     bib
    0.47
     bibli
    0.44
    boo
    0.41
     bí
    0.41
     boo
    0.41
    bibli
    0.40
    SHE
    0.40
    Stacks
    0.40
    Act Density 0.003%

    No Known Activations