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

    Neuronpedia

    INDEX
    Explanations

    state described by past participle and agent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     strongly
    1.00
     সঠিকভাবে
    0.98
     Strongly
    0.95
     indicating
    0.95
    真的很
    0.88
    이랑
    0.87
     indiquant
    0.86
    是非常
    0.86
    非常的
    0.84
    積極
    0.83
    POSITIVE LOGITS
     unwittingly
    0.98
     ostensibly
    0.95
     doubtless
    0.92
     improb
    0.89
     nightly
    0.87
     bewild
    0.86
     unwitting
    0.85
     ceas
    0.85
     baffling
    0.82
     stets
    0.81
    Act Density 0.085%

    No Known Activations