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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hardware
    -0.07
    [parent
    -0.07
    楚
    -0.07
     bright
    -0.06
    lexer
    -0.06
    .Program
    -0.06
    “All
    -0.06
    _Comm
    -0.06
    “They
    -0.06
    “And
    -0.06
    POSITIVE LOGITS
     pups
    0.07
     лікування
    0.06
     pk
    0.06
     philippines
    0.06
    sbin
    0.06
    ुलन
    0.06
    (MPI
    0.06
    hoff
    0.06
     glue
    0.06
    912
    0.06
    Act Density 0.036%

    No Known Activations