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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     updated
    -0.07
     SV
    -0.07
     Ideas
    -0.06
     Appointment
    -0.06
    OVE
    -0.06
     humans
    -0.06
    ESSAGE
    -0.06
     adults
    -0.06
     EW
    -0.06
     Love
    -0.06
    POSITIVE LOGITS
    sunuz
    0.07
    joint
    0.07
    _proxy
    0.06
    .props
    0.06
    Entered
    0.06
    .emit
    0.06
     �
    0.06
    .refresh
    0.06
    ώνα
    0.06
    _tex
    0.06
    Act Density 0.007%

    No Known Activations