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

    Neuronpedia

    INDEX
    Explanations

    network IP address

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Moss
    0.52
     Ced
    0.51
    ס
    0.50
     Aplikasi
    0.49
    𝘨
    0.48
     Avila
    0.47
     Cec
    0.47
     Elis
    0.47
     Medved
    0.46
     Regul
    0.46
    POSITIVE LOGITS
    sided
    0.47
    inc
    0.46
    cell
    0.45
    phone
    0.44
    không
    0.44
    tol
    0.44
    phon
    0.43
    ty
    0.43
    phi
    0.43
    phones
    0.43
    Act Density 0.003%

    No Known Activations