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

    Neuronpedia

    INDEX
    Explanations

    list items and details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    0.38
     અને
    0.36
     apprend
    0.33
     mitologia
    0.33
    ၊
    0.31
     watersheds
    0.31
    <0xF3>
    0.30
     advogado
    0.30
     epochs
    0.29
     ciencias
    0.29
    POSITIVE LOGITS
    S
    0.36
    T
    0.34
     M
    0.31
    M
    0.29
    R
    0.29
    P
    0.29
     Multiple
    0.28
     Movement
    0.28
    N
    0.28
    E
    0.28
    Act Density 1.408%

    No Known Activations