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

    Neuronpedia

    INDEX
    Explanations

    programming questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wreck
    -0.08
     cards
    -0.07
     JE
    -0.07
     deux
    -0.07
    ميم
    -0.07
     frontal
    -0.06
     klein
    -0.06
     negligence
    -0.06
     minimize
    -0.06
    soft
    -0.06
    POSITIVE LOGITS
     quelque
    0.07
    /style
    0.07
    round
    0.06
     Serbia
    0.06
     Provincial
    0.06
    ButtonType
    0.06
    ppelin
    0.06
    -CN
    0.06
     erotica
    0.06
    توبر
    0.06
    Act Density 0.104%

    No Known Activations