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

    Neuronpedia

    INDEX
    Explanations

    `.` followed by identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     b
    1.24
     r
    1.21
     p
    1.18
     m
    1.13
     c
    1.13
     f
    1.12
     v
    1.11
     z
    1.09
     d
    1.06
     iv
    1.03
    POSITIVE LOGITS
    C
    1.59
    W
    1.53
    B
    1.51
    G
    1.51
    E
    1.51
    Y
    1.50
    R
    1.49
    S
    1.48
    M
    1.48
    F
    1.47
    Act Density 0.361%

    No Known Activations