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

    Neuronpedia

    INDEX
    Explanations

    home + context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lower
    0.84
    Լ
    0.84
     HomeComponent
    0.84
     Lower
    0.80
     lower
    0.80
    வாக
    0.78
     อี
    0.78
    ע
    0.77
    進
    0.76
    ન્ટ
    0.76
    POSITIVE LOGITS
    brew
    1.58
    grown
    1.49
    AsUp
    1.47
    ownership
    1.43
    AsUpIndicator
    1.39
     tangga
    1.37
    opathic
    1.34
     sakit
    1.33
    comings
    1.29
    owners
    1.26
    Act Density 0.090%

    No Known Activations