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

    Neuronpedia

    INDEX
    Explanations

    time duration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    いただいた
    -0.07
     hữu
    -0.07
    um
    -0.07
    ementia
    -0.07
    _behavior
    -0.06
    éré
    -0.06
     further
    -0.06
    .__
    -0.06
     lithium
    -0.06
     części
    -0.06
    POSITIVE LOGITS
     miesz
    0.08
    planes
    0.08
    �
    0.07
     Hands
    0.07
    Pad
    0.07
     Saturdays
    0.07
     sv
    0.07
     TLS
    0.07
     Effects
    0.07
    incl
    0.07
    Act Density 0.042%

    No Known Activations