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

    Neuronpedia

    INDEX
    Explanations

    Miscellaneous text and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Template
    -0.07
     sinful
    -0.06
    veh
    -0.06
     oppressed
    -0.06
    ляється
    -0.06
     lockdown
    -0.06
     blades
    -0.06
     refute
    -0.06
     Rafael
    -0.06
    .Search
    -0.05
    POSITIVE LOGITS
    ้าอ
    0.07
     farther
    0.06
    дн
    0.06
     MQ
    0.06
     touchscreen
    0.06
    @admin
    0.06
     bedside
    0.06
    нання
    0.06
    ileaks
    0.06
     maternity
    0.06
    Act Density 0.018%

    No Known Activations