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

    Neuronpedia

    INDEX
    Explanations

    outlining, detailing, recounting, recalling, traces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     de
    0.59
     on
    0.57
     le
    0.52
     c
    0.52
     HIPAA
    0.50
     WC
    0.50
     médicos
    0.50
     met
    0.49
     ডাক্ত
    0.49
     mastermind
    0.49
    POSITIVE LOGITS
    膻
    0.59
    zięk
    0.54
    barplot
    0.53
    SFR
    0.49
     winding
    0.49
    bankruptcy
    0.48
    vintage
    0.47
    kke
    0.47
    curly
    0.47
    winding
    0.47
    Act Density 0.021%

    No Known Activations