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

    Neuronpedia

    INDEX
    Explanations

    how things perform or interact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.55
    ש
    0.50
    个
    0.50
    0.49
    s
    0.47
    .;
    0.45
    5
    0.44
    ه
    0.43
    events
    0.43
     individuales
    0.43
    POSITIVE LOGITS
     prohibitive
    0.48
    यों
    0.47
    ിലും
    0.47
    iyordu
    0.46
    uper
    0.45
    ಸ್ಥ
    0.45
    planetary
    0.44
     semidefinite
    0.44
     QCD
    0.44
     स्वप्
    0.44
    Act Density 0.000%

    No Known Activations