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

    Neuronpedia

    INDEX
    Explanations

    Sanitizers in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    üne
    -0.07
     التو
    -0.06
    _pw
    -0.06
     lad
    -0.06
     sling
    -0.06
     bursts
    -0.06
     wave
    -0.06
    brakk
    -0.06
    Revision
    -0.06
    POSITIVE LOGITS
     Insecta
    0.07
    .Priority
    0.06
    たく
    0.06
     marque
    0.06
     Developing
    0.06
     dospěl
    0.06
     정확
    0.06
     soda
    0.05
     motivating
    0.05
    rey
    0.05
    Act Density 0.013%

    No Known Activations