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

    Neuronpedia

    INDEX
    Explanations

    the followed by specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eyewear
    0.39
     retrie
    0.39
     visuals
    0.39
     retrospective
    0.38
     enigma
    0.38
     beginnings
    0.38
     daff
    0.37
     palindrome
    0.36
     solvers
    0.36
     editorials
    0.36
    POSITIVE LOGITS
    s
    0.47
     consecuencia
    0.45
     precisión
    0.45
    en
    0.45
     condições
    0.44
     necessário
    0.44
    lu
    0.43
     diámetro
    0.43
    č
    0.43
     quelli
    0.43
    Act Density 0.036%

    No Known Activations