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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RING
    -0.06
    jedn
    -0.06
    regs
    -0.06
    .StringUtils
    -0.06
    stock
    -0.05
    .ab
    -0.05
     scrambled
    -0.05
     frogs
    -0.05
    ’de
    -0.05
     росій
    -0.05
    POSITIVE LOGITS
    OWN
    0.08
     specifications
    0.07
    Ms
    0.07
     hopeless
    0.07
    ablish
    0.07
     DPI
    0.07
    Marsh
    0.07
     frightening
    0.07
    _Panel
    0.07
    range
    0.07
    Act Density 0.008%

    No Known Activations