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

    Neuronpedia

    INDEX
    Explanations

    printing output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     moonlight
    0.42
     જય
    0.40
    ineties
    0.39
     bost
    0.38
    োন
    0.38
     ลอง
    0.38
     PM
    0.36
     Zad
    0.36
     nedir
    0.36
     substrates
    0.36
    POSITIVE LOGITS
    atil
    0.41
    shear
    0.40
    posable
    0.39
    加えて
    0.39
    魂
    0.39
     Console
    0.37
    touch
    0.37
    Console
    0.37
    saw
    0.37
    ulation
    0.36
    Act Density 0.001%

    No Known Activations