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

    Neuronpedia

    INDEX
    Explanations

    agreement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .pose
    -0.07
     Recommendation
    -0.07
    hunt
    -0.07
    urança
    -0.07
     Reflection
    -0.07
     Paso
    -0.06
    agus
    -0.06
    -response
    -0.06
     Soccer
    -0.06
    -files
    -0.06
    POSITIVE LOGITS
    =".$
    0.06
    0.06
    ALLOW
    0.06
    Không
    0.06
    /'↵
    0.06
    coh
    0.06
    UsingEncoding
    0.06
    ?]
    0.06
     CSP
    0.06
     云
    0.06
    Act Density 0.013%

    No Known Activations