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

    Neuronpedia

    INDEX
    Explanations

    reporting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     busca
    -0.08
     claims
    -0.07
     distances
    -0.07
     composite
    -0.07
    Stretch
    -0.07
     fue
    -0.07
     jog
    -0.07
    parity
    -0.07
     Composite
    -0.07
     profile
    -0.07
    POSITIVE LOGITS
    DECLARE
    0.06
     San
    0.06
    _Bl
    0.06
    iddleware
    0.06
     pcb
    0.06
     ediyorum
    0.06
     лим
    0.06
     Adobe
    0.05
    UGE
    0.05
    idious
    0.05
    Act Density 0.115%

    No Known Activations