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

    Neuronpedia

    INDEX
    Explanations

    clearing chips

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dz
    0.57
    a
    0.50
    dg
    0.48
    dv
    0.47
    d
    0.47
    "-
    0.46
    .",
    0.45
    dx
    0.44
    dh
    0.44
    "/
    0.43
    POSITIVE LOGITS
     approfond
    0.50
    ल
    0.49
    ḵ
    0.48
    ழை
    0.48
     activity
    0.47
    פי
    0.47
    रण
    0.46
    াবেক
    0.46
     knew
    0.44
     अपना
    0.44
    Act Density 0.000%

    No Known Activations