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

    Neuronpedia

    INDEX
    Explanations

    company innovation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     blackmail
    0.84
     panicked
    0.76
     nerfs
    0.76
     excretion
    0.75
     incriminating
    0.71
     worksheet
    0.70
     preliminary
    0.70
     assays
    0.70
     ژان
    0.68
     panic
    0.67
    POSITIVE LOGITS
     innovation
    1.75
     innovators
    1.72
    Innovation
    1.70
     innovación
    1.70
    innovation
    1.69
    创新
    1.61
     Innovation
    1.60
     иннова
    1.60
     innovate
    1.52
     혁
    1.52
    Act Density 0.329%

    No Known Activations