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

    Neuronpedia

    INDEX
    Explanations

    bracing, covering, defining, calculating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    0.61
    고
    0.56
    synchron
    0.54
    ୌ
    0.54
    of
    0.53
    αν
    0.52
    Y
    0.52
    risk
    0.51
    two
    0.51
    carriage
    0.51
    POSITIVE LOGITS
    怎样的
    0.50
     Reverso
    0.46
    きたいと思います
    0.46
     reconnaît
    0.45
     Robot
    0.44
     Cambio
    0.44
     저희
    0.44
     Rydberg
    0.43
     Robo
    0.42
     Tipo
    0.42
    Act Density 0.000%

    No Known Activations