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

    Neuronpedia

    INDEX
    Explanations

    names followed by descriptive suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     waivers
    0.29
     HIV
    0.28
     guar
    0.28
     Aztec
    0.27
     UHF
    0.27
     Congress
    0.26
     codec
    0.26
     AIDS
    0.26
     casein
    0.26
     Interpol
    0.26
    POSITIVE LOGITS
    ari
    0.36
    ado
    0.36
    aj
    0.35
    4
    0.33
    bl
    0.32
    jan
    0.32
    ita
    0.32
    ando
    0.31
    ank
    0.31
    3
    0.31
    Act Density 0.006%

    No Known Activations