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

    Neuronpedia

    INDEX
    Explanations

    ANY

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ──
    -0.06
     RH
    -0.06
    styled
    -0.06
    msgs
    -0.06
     hư
    -0.06
     msg
    -0.06
     FW
    -0.06
    .Collections
    -0.06
    xCF
    -0.06
    .datab
    -0.06
    POSITIVE LOGITS
     varsa
    0.08
     companyId
    0.07
    итай
    0.07
     Ub
    0.07
    >'+↵
    0.07
     geldi
    0.06
    {}{↵
    0.06
     tyranny
    0.06
     falta
    0.06
    unan
    0.06
    Act Density 0.001%

    No Known Activations