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

    Neuronpedia

    INDEX
    Explanations

    say "ography"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     γνω
    -0.06
    zhou
    -0.06
     flooding
    -0.06
     Fus
    -0.06
    cue
    -0.06
    Checked
    -0.06
     rocket
    -0.06
     shocks
    -0.06
     debug
    -0.06
     basement
    -0.06
    POSITIVE LOGITS
    .Unmarshal
    0.07
    AREST
    0.06
    ACY
    0.06
    RESH
    0.06
     Gdk
    0.06
    >_
    0.06
    pector
    0.06
    tiv
    0.06
    avored
    0.06
    antlr
    0.06
    Act Density 0.001%

    No Known Activations