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

    Neuronpedia

    INDEX
    Explanations

    parentheses and colors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     👍
    0.55
     heinous
    0.54
     "
    0.54
     😊
    0.52
     PayPal
    0.51
    </li>
    0.50
     cruel
    0.49
    });
    0.49
     checkboxes
    0.49
     });
    0.48
    POSITIVE LOGITS
    ást
    0.63
    keleton
    0.53
     energi
    0.52
    óż
    0.52
     adjoint
    0.52
    लास
    0.51
    chnitt
    0.51
    oselect
    0.51
    énd
    0.50
     conjugates
    0.50
    Act Density 0.000%

    No Known Activations