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

    Neuronpedia

    INDEX
    Explanations

    Management Studio, maternity, feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ligands
    0.46
     spasms
    0.45
     eyelashes
    0.42
     spectrosc
    0.40
     ovipares
    0.40
     associée
    0.40
    𝜎
    0.40
     anastomosis
    0.38
     hissed
    0.38
     équipe
    0.38
    POSITIVE LOGITS
    www
    0.44
    em
    0.38
    fb
    0.35
    يه
    0.34
    sorry
    0.34
    settings
    0.34
    el
    0.33
     www
    0.33
    eu
    0.33
    preview
    0.33
    Act Density 0.001%

    No Known Activations