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

    Neuronpedia

    INDEX
    Explanations

    potential for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    年の
    0.54
    Vanilla
    0.51
    จัย
    0.47
    Rose
    0.46
    χεί
    0.46
    Jazz
    0.45
    CartVO
    0.45
    $=\
    0.45
    Ju
    0.45
    Mental
    0.44
    POSITIVE LOGITS
    nd
    0.45
    ty
    0.45
    trab
    0.45
    scheduler
    0.44
    un
    0.43
    modo
    0.43
    anned
    0.42
    llen
    0.42
    te
    0.42
    ism
    0.42
    Act Density 0.000%

    No Known Activations