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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ES
    -0.06
     Dane
    -0.06
    (Duration
    -0.06
    (R
    -0.06
     crimson
    -0.06
     ro
    -0.06
    deliver
    -0.06
     الحياة
    -0.06
     जन
    -0.05
    ein
    -0.05
    POSITIVE LOGITS
    kla
    0.07
    rog
    0.07
     Αρ
    0.06
    �
    0.06
    _UINT
    0.06
    unds
    0.06
    gements
    0.06
     dados
    0.06
    gif
    0.06
     envision
    0.06
    Act Density 0.036%

    No Known Activations