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

    Neuronpedia

    INDEX
    Explanations

    dot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interpersonal
    -0.07
     ACK
    -0.07
     άν
    -0.07
     Bf
    -0.07
     maxx
    -0.07
    ynamodb
    -0.07
    OLF
    -0.07
    _inv
    -0.06
     shl
    -0.06
     Swan
    -0.06
    POSITIVE LOGITS
    ons
    0.07
     reducer
    0.06
    	URL
    0.06
    �
    0.06
    *
    0.06
    patial
    0.06
     debating
    0.06
    uzione
    0.06
    uffix
    0.06
     spos
    0.06
    Act Density 0.000%

    No Known Activations