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

    Neuronpedia

    INDEX
    Explanations

    specific names or terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    खंड
    0.61
     Preventing
    0.60
     Containing
    0.59
     Minnesota
    0.59
    പ്പോഴും
    0.58
    ਮੀ
    0.57
     Phosphate
    0.57
     mencegah
    0.57
     Mariano
    0.56
    urum
    0.56
    POSITIVE LOGITS
    Evalu
    0.74
    Evaluate
    0.67
     eva
    0.64
    Eval
    0.64
    full
    0.63
     evaluate
    0.63
    evaluate
    0.61
     Evalu
    0.61
    straight
    0.61
     evalu
    0.61
    Act Density 0.001%

    No Known Activations