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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dashboard
    -0.08
     hoc
    -0.07
    不舍
    -0.07
    ߜ
    -0.07
    敦
    -0.07
     대해서
    -0.07
    խ
    -0.07
    保温
    -0.07
    𝘫
    -0.07
    ᵌ
    -0.07
    POSITIVE LOGITS
     strlen
    0.07
     specializing
    0.07
    вин
    0.07
    _char
    0.07
     Iron
    0.07
     CIA
    0.07
     Microsoft
    0.06
     PHP
    0.06
    .access
    0.06
     Tray
    0.06
    Act Density 0.004%

    No Known Activations