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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     konuştu
    -0.07
    عاد
    -0.07
    eping
    -0.07
     dicho
    -0.07
    aines
    -0.06
    pped
    -0.06
    _info
    -0.06
    ofs
    -0.06
    sta
    -0.06
    ΙΔ
    -0.06
    POSITIVE LOGITS
    (/^
    0.06
    vol
    0.06
     MLA
    0.06
     brows
    0.06
     Pel
    0.06
     メ
    0.05
     Wrest
    0.05
    285
    0.05
     Kal
    0.05
     grac
    0.05
    Act Density 0.629%

    No Known Activations