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

    Neuronpedia

    INDEX
    Explanations

    higher, exploring, swim, firm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Subset
    0.50
    Dublin
    0.49
    Housing
    0.48
    Conceptual
    0.48
    Russian
    0.47
    Circular
    0.47
    Reduced
    0.47
    Barcelona
    0.46
    Union
    0.46
    Irish
    0.46
    POSITIVE LOGITS
    o
    0.51
    innerApiCalls
    0.50
     levando
    0.49
     Gideon
    0.47
     clockRadius
    0.47
    gleichen
    0.47
    zték
    0.46
    u
    0.46
    lena
    0.46
     Cattle
    0.45
    Act Density 0.000%

    No Known Activations