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

    Neuronpedia

    INDEX
    Explanations

    full

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slightest
    -0.07
    丹
    -0.07
     VLAN
    -0.06
    [train
    -0.06
    pering
    -0.06
    cee
    -0.06
    емон
    -0.06
    匹
    -0.06
     Monsters
    -0.06
    uccess
    -0.06
    POSITIVE LOGITS
    Floating
    0.07
    rial
    0.07
    Outcome
    0.07
    eligible
    0.07
     Floating
    0.06
    .bluetooth
    0.06
     "',
    0.06
    солют
    0.06
    rax
    0.06
     safeguard
    0.06
    Act Density 0.193%

    No Known Activations