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

    Neuronpedia

    INDEX
    Explanations

    ball straight up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Insects
    0.45
     ಇತರ
    0.42
    elig
    0.39
    ဆို
    0.39
     Organization
    0.39
     '".
    0.39
     MACHINE
    0.38
    సీ
    0.38
    加上
    0.38
     CAMERA
    0.38
    POSITIVE LOGITS
    bär
    0.52
     ettha
    0.51
     hydrochloric
    0.50
    hydraz
    0.48
     pabbaj
    0.47
    缑
    0.46
     pavattati
    0.46
     ক্লাশ
    0.46
     hydrophobic
    0.43
     levies
    0.43
    Act Density 0.005%

    No Known Activations