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

    Neuronpedia

    INDEX
    Explanations

    files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.06
    say
    -0.06
     filles
    -0.06
    .break
    -0.06
     deren
    -0.06
     alo
    -0.06
     underneath
    -0.06
     accreditation
    -0.06
    	anim
    -0.06
    十分
    -0.06
    POSITIVE LOGITS
     witnesses
    0.07
    eph
    0.07
     Ensemble
    0.07
     jobs
    0.07
    _MODEL
    0.07
    urrencies
    0.07
     Owned
    0.06
     Robotics
    0.06
     Muse
    0.06
    game
    0.06
    Act Density 0.000%

    No Known Activations