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

    Neuronpedia

    INDEX
    Explanations

    done

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     john
    -0.06
     Robert
    -0.06
    Work
    -0.06
     _
    -0.06
    WORK
    -0.06
    .framework
    -0.06
     blanket
    -0.05
     decrypt
    -0.05
     escalated
    -0.05
    fault
    -0.05
    POSITIVE LOGITS
    ъек
    0.07
     thắng
    0.07
     Bitmap
    0.07
     Cont
    0.07
     sokak
    0.07
     mắc
    0.06
    .tiles
    0.06
     resetting
    0.06
    rename
    0.06
    ornado
    0.06
    Act Density 0.000%

    No Known Activations