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

    Neuronpedia

    INDEX
    Explanations

    code/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Flavor
    -0.07
     Like
    -0.07
    如
    -0.07
    .Auth
    -0.06
    /V
    -0.06
     Aux
    -0.06
     BET
    -0.06
     snapped
    -0.06
     wie
    -0.06
     руб
    -0.06
    POSITIVE LOGITS
    .uint
    0.06
    _codes
    0.06
    iễn
    0.06
    减
    0.06
    implement
    0.06
     fer
    0.06
     Jeremiah
    0.06
    plementation
    0.06
     indifferent
    0.06
     Григор
    0.06
    Act Density 0.000%

    No Known Activations