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

    Neuronpedia

    INDEX
    Explanations

    code syntax and data types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اتا
    0.38
    அத
    0.37
    anskrit
    0.37
    guests
    0.37
    iją
    0.36
    ichiro
    0.36
    નેસ
    0.35
     अनाउंस
    0.33
    🕣
    0.33
    atience
    0.33
    POSITIVE LOGITS
     depos
    0.33
     sincere
    0.33
     shipped
    0.31
     inhibit
    0.31
     enf
    0.30
     E
    0.30
     blockers
    0.30
     bodily
    0.29
     cuttings
    0.29
     F
    0.29
    Act Density 0.001%

    No Known Activations