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

    Neuronpedia

    INDEX
    Explanations

    friendly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .paper
    -0.08
     MCU
    -0.07
     aktuellen
    -0.06
    Grad
    -0.06
     getUsers
    -0.06
     dependent
    -0.06
    .Ac
    -0.06
    �
    -0.06
    chein
    -0.06
    igit
    -0.06
    POSITIVE LOGITS
    -friendly
    0.12
    riendly
    0.08
     billig
    0.07
    friendly
    0.07
     terrorist
    0.07
     باید
    0.07
     friendly
    0.07
     democratic
    0.07
     counterpart
    0.06
    Lint
    0.06
    Act Density 0.005%

    No Known Activations