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

    Neuronpedia

    INDEX
    Explanations

    before, after, or as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    icamente
    0.57
    Με
    0.56
    pp
    0.54
     entonces
    0.54
     ainsi
    0.53
    ivasena
    0.53
    ul
    0.52
    ggi
    0.52
    bt
    0.51
    ud
    0.50
    POSITIVE LOGITS
    暠
    0.56
     rudder
    0.46
    Constraints
    0.46
     $/
    0.45
     cyclohexane
    0.45
     hydrothermal
    0.45
     azal
    0.45
    욘
    0.45
    yiz
    0.45
     ):
    0.44
    Act Density 0.918%

    No Known Activations