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

    Neuronpedia

    INDEX
    Explanations

    positivity and embracing change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     forest
    -0.07
    ammo
    -0.07
     morb
    -0.07
     precedence
    -0.07
    abad
    -0.06
    .visitInsn
    -0.06
     pane
    -0.06
     ayında
    -0.06
    becca
    -0.06
    prite
    -0.06
    POSITIVE LOGITS
    ;",
    0.07
     dělat
    0.06
     ;
↵
↵
    0.06
     FLOAT
    0.06
     newState
    0.06
    atetime
    0.06
     yakın
    0.06
     pulled
    0.06
     Dış
    0.06
     parti
    0.06
    Act Density 0.167%

    No Known Activations