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

    Neuronpedia

    INDEX
    Explanations

    Section headings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gy
    -0.50
     rote
    -0.44
    ly
    -0.42
    s
    -0.40
    toxicity
    -0.40
    v
    -0.39
    └──
    -0.36
     
    -0.36
    dys
    -0.36
    E
    -0.36
    POSITIVE LOGITS
     Paglinawan
    1.18
    #+#
    1.04
     ligiloj
    1.03
     '\\;'
    0.98
    Vidite
    0.96
     include
    0.93
     <>",
    0.93
    ThroughAttribute
    0.92
    CppMethod
    0.92
    principalTable
    0.91
    Act Density 0.025%

    No Known Activations