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

    Neuronpedia

    INDEX
    Explanations

    connecting to the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     genug
    0.48
     molecules
    0.47
     fluctuations
    0.47
     circula
    0.47
     assumptions
    0.44
     circul
    0.44
     moléculas
    0.44
     exercises
    0.43
     kerjasama
    0.43
     muy
    0.43
    POSITIVE LOGITS
    은
    0.53
    Refund
    0.51
    并没有
    0.50
     사용자
    0.49
    Standard
    0.48
    码
    0.48
    选项
    0.47
    Saf
    0.47
    硬盘
    0.47
    账户
    0.47
    Act Density 0.007%

    No Known Activations