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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pParent
    -0.08
     forward
    -0.07
     #__
    -0.07
     forwarded
    -0.07
     motivation
    -0.07
     choosing
    -0.06
     Agent
    -0.06
    (reinterpret
    -0.06
    ossed
    -0.06
    MainThread
    -0.06
    POSITIVE LOGITS
    还是
    0.07
    하면서
    0.07
    :Is
    0.07
     ici
    0.07
    jis
    0.07
    Bes
    0.07
    ข
    0.07
    ﾉ
    0.07
    —is
    0.07
     is
    0.07
    Act Density 0.024%

    No Known Activations