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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Γου
    -0.07
     thermostat
    -0.06
     lokal
    -0.06
     Zhou
    -0.06
     emojis
    -0.06
     itm
    -0.06
     téc
    -0.06
     Carla
    -0.06
    oho
    -0.06
    átel
    -0.06
    POSITIVE LOGITS
     Uh
    0.07
    skill
    0.06
    [V
    0.06
     fine
    0.06
    /logs
    0.06
     contributes
    0.06
     erase
    0.06
     details
    0.06
    _por
    0.06
    uments
    0.06
    Act Density 0.000%

    No Known Activations