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

    Neuronpedia

    INDEX
    Explanations

    Code/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Current
    -0.07
    _TRACK
    -0.07
    ↵     ↵
    -0.07
    faith
    -0.06
    PushMatrix
    -0.06
    ottom
    -0.06
     عش
    -0.06
    :NSUTF
    -0.06
    Projectile
    -0.06
     spike
    -0.06
    POSITIVE LOGITS
     thumbnail
    0.07
     buffered
    0.07
     thriving
    0.07
     timestamp
    0.07
    	yield
    0.07
    profits
    0.06
     environmentally
    0.06
    requirements
    0.06
     throttle
    0.06
     +#+#+#+
    0.06
    Act Density 0.000%

    No Known Activations