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

    Neuronpedia

    INDEX
    Explanations

    global hostility, capsules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    irinha
    0.41
    zał
    0.39
     الطل
    0.36
     prerogative
    0.36
    日上午
    0.36
    iciary
    0.36
     stairway
    0.35
    buri
    0.35
    আচ্ছা
    0.34
    ጨ
    0.34
    POSITIVE LOGITS
     Capsules
    0.54
     Capsule
    0.53
    Se
    0.53
     capsules
    0.52
     capsule
    0.48
     Se
    0.47
    Connections
    0.44
     Connections
    0.43
    caps
    0.42
    Caps
    0.42
    Act Density 0.000%

    No Known Activations