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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	with
    -0.07
     weigh
    -0.07
    Tr
    -0.07
     Attr
    -0.07
     benchmarks
    -0.07
     faults
    -0.06
     reaching
    -0.06
    [(
    -0.06
    Ber
    -0.06
    .press
    -0.06
    POSITIVE LOGITS
    衣
    0.06
     Libya
    0.06
    생
    0.06
     Celtics
    0.06
    ListItem
    0.06
     Dorothy
    0.06
    Outcome
    0.05
    .');
    0.05
     سوال
    0.05
    ampie
    0.05
    Act Density 0.000%

    No Known Activations