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

    Neuronpedia

    INDEX
    Explanations

    warnings and safety

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hostages
    -0.06
    	 ↵
    -0.06
     Fate
    -0.06
    Tank
    -0.06
     //}↵↵
    -0.06
    』（
    -0.06
    ();

↵
    -0.06
    proof
    -0.06
    .definition
    -0.06
     Затем
    -0.05
    POSITIVE LOGITS
    omon
    0.07
    jal
    0.07
    Indented
    0.07
    icha
    0.06
     trading
    0.06
     HEX
    0.06
     Circular
    0.06
     estate
    0.06
     apology
    0.06
     wishing
    0.06
    Act Density 0.044%

    No Known Activations