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

    Neuronpedia

    INDEX
    Explanations

    giants and dwarfs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CIRCUIT
    0.42
     culoare
    0.42
     CIRCU
    0.40
    หัส
    0.38
     কঠিন
    0.38
     زیب
    0.38
    Circuit
    0.36
     தேர்
    0.36
     oxidized
    0.36
    erenza
    0.36
    POSITIVE LOGITS
    巨人
    1.10
     giants
    1.03
     dwarf
    0.93
     towering
    0.93
     Giants
    0.91
    Giant
    0.91
     Giant
    0.91
    giants
    0.91
     dwar
    0.90
     dwarfs
    0.89
    Act Density 0.055%

    No Known Activations