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

    Neuronpedia

    INDEX
    Explanations

    based on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     தேர்வு
    0.41
     decision
    0.39
    寄せ
    0.38
     entre
    0.37
     colleg
    0.37
     nationale
    0.37
    ুদের
    0.36
     goto
    0.36
     canals
    0.36
     collab
    0.36
    POSITIVE LOGITS
     воору
    0.37
     enfermedad
    0.37
     დიდ
    0.36
    ాలే
    0.36
    電圧
    0.35
    생활
    0.35
    ベビー
    0.35
     وړیا
    0.34
    ERNAL
    0.34
     Babies
    0.34
    Act Density 0.003%

    No Known Activations