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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    frauen
    -0.06
    izin
    -0.06
    Doctors
    -0.06
     tumors
    -0.06
    -slot
    -0.06
     Заг
    -0.06
    iplina
    -0.06
    kara
    -0.06
    erosis
    -0.06
    textarea
    -0.06
    POSITIVE LOGITS
     may
    0.08
    ropolis
    0.06
     makeshift
    0.06
    ил
    0.06
    <Model
    0.06
     Programming
    0.06
     grate
    0.06
     travels
    0.06
     algunos
    0.06
    关键
    0.06
    Act Density 0.000%

    No Known Activations