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

    Neuronpedia

    INDEX
    Explanations

    Dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     passphrase
    -0.08
    ाण
    -0.08
     catering
    -0.07
     Crate
    -0.06
     perpetrators
    -0.06
    _Camera
    -0.06
    src
    -0.06
     test
    -0.06
     taper
    -0.06
     breakup
    -0.06
    POSITIVE LOGITS
    áj
    0.07
    ３
    0.06
     gard
    0.06
    الف
    0.06
    >'.$
    0.06
    skb
    0.06
    Equ
    0.06
    ★
    0.06
     Lin
    0.06
     TI
    0.06
    Act Density 0.122%

    No Known Activations