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

    Neuronpedia

    INDEX
    Explanations

    eel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <H
    -0.07
    <E
    -0.07
    ⩽
    -0.07
    -{
    -0.07
     away
    -0.07
    xbc
    -0.06
    (skb
    -0.06
    <IM
    -0.06
     STUD
    -0.06
    +"/"+
    -0.06
    POSITIVE LOGITS
    影
    0.09
     Andrew
    0.07
     Tubes
    0.07
    jaw
    0.07
    时空
    0.07
    uento
    0.07
     punching
    0.06
    伊拉
    0.06
     millones
    0.06
    eña
    0.06
    Act Density 0.001%

    No Known Activations