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

    Neuronpedia

    INDEX
    Explanations

    Comfort and rest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    воз
    -0.07
     fries
    -0.07
    (jButton
    -0.06
     emiss
    -0.06
    rone
    -0.06
     Engl
    -0.06
     adventurous
    -0.06
    فتم
    -0.06
    Carbon
    -0.06
     bumped
    -0.06
    POSITIVE LOGITS
     ([]
    0.07
    进
    0.07
    -standard
    0.07
    :numel
    0.07
     státy
    0.07
     organising
    0.06
    ->$
    0.06
     boost
    0.06
    {Name
    0.06
    adf
    0.06
    Act Density 0.287%

    No Known Activations