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

    Neuronpedia

    INDEX
    Explanations

    zones, types, Mage, export

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ید
    0.66
    に
    0.60
    is
    0.59
     cuore
    0.59
    으로
    0.57
    ため
    0.57
     ಒಂದು
    0.56
    에
    0.56
    문의
    0.56
     ljubav
    0.56
    POSITIVE LOGITS
    0.59
    </sup>
    0.57
    </b>
    0.51
     Johnson
    0.50
     anticipated
    0.48
    <h3>
    0.48
    }$
    0.46
    <h4>
    0.46
     men
    0.45
    kj
    0.44
    Act Density 0.001%

    No Known Activations