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

    Neuronpedia

    INDEX
    Explanations

    Technical discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     forgive
    -0.07
     kou
    -0.06
     Oliver
    -0.06
     Cath
    -0.06
     realised
    -0.06
    з
    -0.06
     solves
    -0.06
     Cot
    -0.06
     pew
    -0.06
     yasak
    -0.06
    POSITIVE LOGITS
    	hs
    0.07
                                            ↵
    0.07
    关系
    0.06
      ↵
    0.06
     hypertension
    0.06
    NotSupportedException
    0.06
    Person
    0.06
    ,'#
    0.06
                                                ↵
    0.06
    _ap
    0.06
    Act Density 0.000%

    No Known Activations