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

    Neuronpedia

    INDEX
    Explanations

    new sources, singular values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chromos
    0.40
     deny
    0.38
    िका
    0.37
     chromium
    0.37
     send
    0.37
     affer
    0.37
     Straße
    0.36
     satisfy
    0.35
     BEAUT
    0.35
     STREET
    0.35
    POSITIVE LOGITS
     مسئلے
    0.36
    অভ
    0.36
    രിച്ച
    0.36
    мова
    0.35
    ৳
    0.35
    ovaný
    0.35
    থমে
    0.35
    ⌘
    0.35
    ucin
    0.34
     ទ
    0.34
    Act Density 0.001%

    No Known Activations