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

    Neuronpedia

    INDEX
    Explanations

    neural network weights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    0.59
    ↵
    0.55
     -
    0.54
    0.54
    '
    0.49
    Link
    0.48
    My
    0.48
     )
    0.47
     –
    0.45
    API
    0.45
    POSITIVE LOGITS
    }^{*}=
    0.58
    }$=
    0.54
     کشمیر
    0.54
     posteriores
    0.52
    akl
    0.52
     wyra
    0.50
    сія
    0.50
    <unused72>
    0.49
    PLEX
    0.49
    ᴙ
    0.49
    Act Density 0.005%

    No Known Activations