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

    Neuronpedia

    INDEX
    Explanations

    physics concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desktop
    0.54
     passion
    0.53
     Globe
    0.52
     splendour
    0.50
     globe
    0.50
     stardom
    0.49
     resource
    0.48
     threats
    0.48
    ळ
    0.48
     geldi
    0.47
    POSITIVE LOGITS
     ఏం
    0.51
     siehe
    0.51
     মহম্মদ
    0.50
    큥
    0.50
     Olha
    0.49
     numberOf
    0.48
    αρ
    0.48
     खुशख
    0.48
    decorate
    0.48
    𒊩
    0.48
    Act Density 0.000%

    No Known Activations