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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    💫
    -0.07
    hton
    -0.07
    iffs
    -0.07
    =__
    -0.07
    锲
    -0.06
     Hammer
    -0.06
    נצח
    -0.06
     fascination
    -0.06
     quir
    -0.06
     ierr
    -0.06
    POSITIVE LOGITS
     с
    0.08
    接受了
    0.07
    AXB
    0.07
    _ALLOC
    0.07
     few
    0.07
    덤
    0.07
    _ix
    0.07
    购买
    0.06
    '\
    0.06
    곶
    0.06
    Act Density 0.002%

    No Known Activations