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

    Neuronpedia

    INDEX
    Explanations

    Here's a breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     preko
    0.47
    Vent
    0.46
    过
    0.46
    Bar
    0.45
    Seg
    0.45
    Lang
    0.44
    質量
    0.44
    Pod
    0.43
    Fig
    0.43
    Over
    0.43
    POSITIVE LOGITS
     exacerbated
    0.53
     灬
    0.50
     substituents
    0.49
     endanger
    0.48
     anore
    0.47
     secretive
    0.47
     innoc
    0.47
     enzimas
    0.47
    ikopter
    0.46
     endangering
    0.46
    Act Density 0.001%

    No Known Activations