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

    Neuronpedia

    INDEX
    Explanations

    stating purpose or action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tk
    0.49
     bra
    0.48
     ब्राउन
    0.48
    ts
    0.48
    us
    0.48
     froze
    0.48
    𝟰
    0.48
    tt
    0.47
    TAU
    0.47
    ta
    0.46
    POSITIVE LOGITS
    Changes
    0.47
     juega
    0.47
    Ivo
    0.47
    Position
    0.45
    ități
    0.45
     thuận
    0.45
     ينا
    0.45
    Through
    0.44
     июле
    0.44
     दौरान
    0.43
    Act Density 0.000%

    No Known Activations