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

    Neuronpedia

    INDEX
    Explanations

    unusual character combinations that indicate code or UK postal codes.

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     host
    -0.98
     hosts
    -0.90
     Host
    -0.81
     HOST
    -0.79
    host
    -0.78
    Host
    -0.77
     Hosts
    -0.74
    hosts
    -0.73
    Hosts
    -0.71
    HOST
    -0.70
    POSITIVE LOGITS
    Traceback
    0.68
    DockStyle
    0.66
     الحره
    0.55
     varandra
    0.55
    AsUp
    0.54
     skydd
    0.53
     LZ
    0.53
    Демографія
    0.52
     picioare
    0.51
     attenuation
    0.50
    Act Density 0.598%

    No Known Activations