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

    Neuronpedia

    INDEX
    Explanations

    industry

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ('{}
    -0.07
     gadget
    -0.07
    нил
    -0.07
    setMessage
    -0.06
    leting
    -0.06
     precise
    -0.06
    Atlas
    -0.06
    ург
    -0.06
     структур
    -0.05
    erd
    -0.05
    POSITIVE LOGITS
    SEMB
    0.07
    ('/')[-
    0.07
     trium
    0.07
     Craw
    0.07
     Premi
    0.07
     datingside
    0.07
    zeigen
    0.06
     beide
    0.06
    jištění
    0.06
     سین
    0.06
    Act Density 0.125%

    No Known Activations