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

    Neuronpedia

    INDEX
    Explanations

    steel structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अन्य
    0.34
     chromatographic
    0.34
     commande
    0.33
     bruger
    0.33
    嘏
    0.32
     এরকম
    0.31
     מש
    0.31
    ärke
    0.31
    ামুটি
    0.31
     jabatan
    0.31
    POSITIVE LOGITS
    ↵
    0.36
    ли
    0.35
    ви
    0.34
    Collision
    0.34
    ه
    0.32
    ко
    0.32
    ва
    0.31
    ネ
    0.31
    它
    0.31
    ца
    0.31
    Act Density 0.083%

    No Known Activations