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

    Neuronpedia

    INDEX
    Explanations

    lateral

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sourcing
    -0.08
     neon
    -0.07
    ’ici
    -0.07
     brasileiros
    -0.07
     staged
    -0.07
    social
    -0.07
    ;↵↵///
    -0.07
     archived
    -0.07
     সামাজিক
    -0.07
     contemporary
    -0.07
    POSITIVE LOGITS
     Handlung
    0.08
     коэффици
    0.08
     "=
    0.08
     uniforme
    0.08
     koos
    0.08
     lijnen
    0.08
     Regeln
    0.08
    .line
    0.08
     ibikorwa
    0.07
     Attach
    0.07
    Act Density 0.003%

    No Known Activations