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

    Neuronpedia

    INDEX
    Explanations

    highest isolation and security

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rsp
    0.47
     envoyer
    0.47
     legno
    0.46
    濋
    0.45
    આ
    0.44
     iniz
    0.43
    च
    0.43
    descricao
    0.42
     intentionally
    0.42
    zyn
    0.42
    POSITIVE LOGITS
     Chemical
    0.52
     Research
    0.49
     Mechanical
    0.48
     Fluid
    0.47
     Movement
    0.47
    work
    0.46
    movement
    0.46
     Computer
    0.46
     Comp
    0.45
     Fuel
    0.45
    Act Density 0.000%

    No Known Activations