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

    Neuronpedia

    INDEX
    Explanations

    last names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Upgrade
    0.36
    Ind
    0.35
     Partition
    0.35
     Function
    0.34
     Github
    0.34
    Layer
    0.34
     default
    0.34
     Default
    0.34
    Transport
    0.34
    as
    0.34
    POSITIVE LOGITS
     Kelly
    0.60
     Smith
    0.59
     Rodgers
    0.53
     Lee
    0.52
     Lewis
    0.52
     Johnson
    0.51
     Evans
    0.50
     Wilson
    0.50
     Mitchell
    0.50
     Harris
    0.49
    Act Density 0.002%

    No Known Activations