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

    Neuronpedia

    INDEX
    Explanations

    conditions and mathematical relations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ке
    0.49
    色
    0.48
    у
    0.46
    вия
    0.45
    г
    0.44
    ра
    0.44
    э
    0.44
    치
    0.43
    ラ
    0.42
    ких
    0.42
    POSITIVE LOGITS
     pacientes
    0.57
     pasien
    0.54
     patients
    0.54
     Patienten
    0.52
     travailleurs
    0.52
     Familien
    0.48
    patients
    0.47
     người
    0.46
     presos
    0.46
     Gly
    0.45
    Act Density 0.003%

    No Known Activations