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

    Neuronpedia

    INDEX
    Explanations

    Amplifier/signal stages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vej
    -0.07
     bandwidth
    -0.07
    734
    -0.07
     eben
    -0.07
    軍
    -0.06
     tying
    -0.06
    freq
    -0.06
    ooky
    -0.06
     Jahren
    -0.06
    ested
    -0.06
    POSITIVE LOGITS
     Operations
    0.07
     Profession
    0.06
     Renders
    0.06
     obligatory
    0.06
    edata
    0.06
    .SUB
    0.06
    _vote
    0.06
     Wise
    0.06
     Cut
    0.06
     tactic
    0.06
    Act Density 0.285%

    No Known Activations