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

    Neuronpedia

    INDEX
    Explanations

    hop you using referral

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     patented
    0.55
     phleg
    0.53
     teak
    0.52
     voce
    0.52
     workout
    0.52
     histology
    0.52
     biceps
    0.51
     prestaciones
    0.51
     plasma
    0.51
     distal
    0.50
    POSITIVE LOGITS
    r
    0.53
    an
    0.52
    l
    0.47
    ie
    0.46
    n
    0.45
    ivil
    0.43
    ้
    0.43
    企业
    0.42
    Quality
    0.42
    u
    0.42
    Act Density 0.011%

    No Known Activations