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

    Neuronpedia

    INDEX
    Explanations

    Offering help

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iva
    -0.07
     massively
    -0.06
     <--
    -0.06
     headlights
    -0.06
     CS
    -0.06
     RSA
    -0.06
    .quick
    -0.06
    collapsed
    -0.06
    _y
    -0.06
     Dwarf
    -0.06
    POSITIVE LOGITS
    REL
    0.08
    τε
    0.07
     Trustees
    0.07
     calidad
    0.07
     nun
    0.07
    NON
    0.07
    午
    0.06
    _usec
    0.06
    Buff
    0.06
    TC
    0.06
    Act Density 0.016%

    No Known Activations