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

    Neuronpedia

    INDEX
    Explanations

    algorithmic applications and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     programas
    0.42
     Programmer
    0.40
     Y
    0.40
     Punt
    0.40
    عة
    0.38
    gment
    0.36
     Matsumoto
    0.36
    O
    0.36
     volcano
    0.36
    ples
    0.35
    POSITIVE LOGITS
     alg
    0.56
     algorithmic
    0.51
    Alg
    0.48
    alg
    0.47
     Alg
    0.47
     audiencia
    0.45
    aság
    0.44
    algorithmic
    0.43
     감사
    0.43
     ALG
    0.42
    Act Density 0.004%

    No Known Activations