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

    Neuronpedia

    INDEX
    Explanations

    r

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Projection
    -0.07
    .|
    -0.07
    .Cap
    -0.06
    oteric
    -0.06
    _CONFIGURATION
    -0.06
    集合
    -0.06
    meyi
    -0.06
     Puppet
    -0.06
    _attrib
    -0.06
     Edit
    -0.06
    POSITIVE LOGITS
    и
    0.08
    (r
    0.07
    _IMM
    0.07
    &r
    0.07
     r
    0.06
     right
    0.06
    _e
    0.06
    otr
    0.06
     hur
    0.06
     front
    0.06
    Act Density 0.005%

    No Known Activations