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

    Neuronpedia

    INDEX
    Explanations

    technology standards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DNS
    -0.07
    								↵
    -0.06
     Platforms
    -0.06
    -wall
    -0.06
    猫
    -0.06
     personne
    -0.06
     Hubbard
    -0.06
     Windows
    -0.06
    							↵
    -0.06
     Fallout
    -0.06
    POSITIVE LOGITS
    emey
    0.07
    ihan
    0.07
     directs
    0.07
    _taken
    0.07
    [r
    0.07
    rPid
    0.06
     echang
    0.06
     asi
    0.06
    тар
    0.06
    esor
    0.06
    Act Density 0.151%

    No Known Activations