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

    Neuronpedia

    INDEX
    Explanations

    to prepare for independence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chou
    0.39
    טח
    0.38
    tran
    0.37
     Tao
    0.36
     choir
    0.36
     Parc
    0.36
     shortstop
    0.35
    탄소년
    0.35
    斑
    0.35
     stoichiometry
    0.35
    POSITIVE LOGITS
    બો
    0.43
     निवड
    0.41
     inspected
    0.40
     Rx
    0.39
    èges
    0.38
    岨
    0.38
    mberg
    0.38
    ɻ
    0.37
     Calcular
    0.37
     Ángeles
    0.37
    Act Density 0.000%

    No Known Activations