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

    Neuronpedia

    INDEX
    Explanations

    SpaceX, space jobs, tourism, transportation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Amherst
    0.77
     Londres
    0.71
     Uruguay
    0.69
     সংস্করণ
    0.68
     AdWords
    0.67
    elijk
    0.66
    uwa
    0.66
    స్క
    0.65
     SCSI
    0.65
     quảng
    0.64
    POSITIVE LOGITS
    II
    0.79
    AN
    0.74
    o
    0.71
     be
    0.71
    ा
    0.67
    tt
    0.67
    III
    0.66
     for
    0.65
    对抗
    0.65
    type
    0.63
    Act Density 0.008%

    No Known Activations