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

    Neuronpedia

    INDEX
    Explanations

    First-person

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Authorities
    -0.07
    EEK
    -0.06
     camps
    -0.06
     Если
    -0.06
     Що
    -0.06
     brethren
    -0.06
     hypocrisy
    -0.06
     Two
    -0.06
    .entities
    -0.06
    ugins
    -0.06
    POSITIVE LOGITS
    	al
    0.06
     спря
    0.06
     VAL
    0.06
    341
    0.06
     Hanson
    0.06
     just
    0.06
     Received
    0.06
    aler
    0.06
    angi
    0.06
    AT
    0.06
    Act Density 0.017%

    No Known Activations