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

    Neuronpedia

    INDEX
    Explanations

    section headers followed by colons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    രുവനന്തപു
    0.31
     হইয়৷
    0.26
    च्युअल
    0.26
     godinu
    0.26
    ണിത്
    0.24
     জীবনের
    0.23
     സംഭവ
    0.23
     arrhythmias
    0.23
     protegido
    0.23
    可视
    0.22
    POSITIVE LOGITS
    :
    0.60
    ：
    0.55
     :
    0.42
    ::
    0.41
    :**
    0.36
    :.
    0.36
    ↵
    0.35
    :-
    0.33
    ↵↵
    0.32
    :</
    0.32
    Act Density 0.387%

    No Known Activations