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

    Neuronpedia

    INDEX
    Explanations

    going to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    1.66
    ﺨ
    1.53
    ু
    1.51
    zelfde
    1.48
    aan
    1.45
    ע
    1.43
    on
    1.40
    al
    1.40
    עת
    1.38
     తెలంగాణ
    1.36
    POSITIVE LOGITS
    {
    2.11
    >
    1.66
    ])$
    1.59
    }
    1.58
    AZIONE
    1.55
    야
    1.53
    OUS
    1.52
    나
    1.48
    {'
    1.47
    ς
    1.45
    Act Density 0.020%

    No Known Activations