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

    Neuronpedia

    INDEX
    Explanations

    enclose the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    னே
    0.52
     reiniciar
    0.51
     licencia
    0.46
     Literatura
    0.45
     secteurs
    0.45
     comunidades
    0.44
    玖章
    0.44
    ື້ນ
    0.44
     Complexes
    0.44
     paradigma
    0.44
    POSITIVE LOGITS
    cos
    0.47
    pi
    0.45
    smart
    0.45
    lover
    0.42
    :
    0.42
    state
    0.42
    post
    0.40
    arms
    0.40
    zw
    0.39
    round
    0.39
    Act Density 14.845%

    No Known Activations