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

    Neuronpedia

    INDEX
    Explanations

    PHP code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ="{{
    -0.07
     blog
    -0.07
     Determines
    -0.07
    EDGE
    -0.07
    \Tests
    -0.07
    ⏌
    -0.06
     %@",
    -0.06
     cres
    -0.06
     DateTimeKind
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Stern
    0.08
     부
    0.07
     banc
    0.07
     abusing
    0.06
     Lis
    0.06
    arden
    0.06
     Walker
    0.06
    	dispatch
    0.06
    -dialog
    0.06
    Port
    0.06
    Act Density 0.053%

    No Known Activations