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

    Neuronpedia

    INDEX
    Explanations

    I followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     put
    0.38
     வா
    0.37
     experiment
    0.37
    JECTION
    0.37
    閫
    0.36
    aport
    0.35
     curious
    0.35
    akun
    0.35
    Raf
    0.35
    標
    0.35
    POSITIVE LOGITS
    Hence
    0.44
     Anyways
    0.41
     anyways
    0.41
    Anyways
    0.40
     Anyway
    0.39
     Hence
    0.38
     Myself
    0.37
    спублі
    0.37
    ാണ
    0.37
    させて頂きます
    0.37
    Act Density 0.002%

    No Known Activations