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

    Neuronpedia

    INDEX
    Explanations

    positive informal descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fucking
    0.72
     fucked
    0.66
    fuck
    0.60
    Fuck
    0.60
     fuck
    0.55
     manifestly
    0.54
     Fuck
    0.53
     shit
    0.52
     bullshit
    0.51
     projective
    0.50
    POSITIVE LOGITS
     kiddos
    0.85
     BFF
    0.70
     veggies
    0.65
     hubby
    0.61
     groovy
    0.61
     bling
    0.60
     strutt
    0.58
     cudd
    0.58
     celebs
    0.58
     foodie
    0.58
    Act Density 0.078%

    No Known Activations