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

    Neuronpedia

    INDEX
    Explanations

    moving

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Floor
    -0.07
     Manchester
    -0.07
     reak
    -0.07
     weekly
    -0.06
     lông
    -0.06
    >Date
    -0.06
     sprung
    -0.06
     looming
    -0.06
    .delete
    -0.06
     fing
    -0.06
    POSITIVE LOGITS
     MX
    0.07
    .",
↵
    0.06
    hai
    0.06
    แฟ
    0.06
    _ten
    0.06
     cảm
    0.06
    mates
    0.06
     Cadillac
    0.06
     अच
    0.06
     necesita
    0.06
    Act Density 0.006%

    No Known Activations