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

    Neuronpedia

    INDEX
    Explanations

    ect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    asp
    -0.07
    urre
    -0.07
    RP
    -0.07
    RS
    -0.07
     Jin
    -0.07
    arp
    -0.07
    ourn
    -0.07
    应在
    -0.07
    Ann
    -0.07
     cray
    -0.06
    POSITIVE LOGITS
    _density
    0.07
    /__
    0.07
     deix
    0.07
    切成
    0.07
    .loader
    0.07
    _Entity
    0.07
    ________
    0.07
     veröffent
    0.07
    cheiden
    0.07
     terminator
    0.07
    Act Density 0.007%

    No Known Activations