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

    Neuronpedia

    INDEX
    Explanations

    ois

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aValue
    -0.07
     HDMI
    -0.07
    -selection
    -0.07
     glEnd
    -0.06
    しゃ
    -0.06
     leash
    -0.06
     condoms
    -0.06
    -set
    -0.06
    strup
    -0.06
    curacy
    -0.06
    POSITIVE LOGITS
    MR
    0.07
    OM
    0.06
     Golf
    0.06
    0.06
     withdrawals
    0.06
    structures
    0.06
     Horror
    0.06
     Postal
    0.06
     Vintage
    0.06
    0.06
    Act Density 0.003%

    No Known Activations